WO2022001213A1

WO2022001213A1 - Congestion control method and corresponding device

Info

Publication number: WO2022001213A1
Application number: PCT/CN2021/082120
Authority: WO
Inventors: 徐威旺; 胡新宇; 程剑; 张亮
Original assignee: 华为技术有限公司
Priority date: 2020-06-30
Filing date: 2021-03-22
Publication date: 2022-01-06
Also published as: CN113873571A

Abstract

Provided in the present application are a congestion control method and a corresponding device, which are used to effectively carry out congestion control on traffic data of different applications, and can improve the utilization rate of network bandwidth resources on the basis of not affecting the experience of a user using the applications. The method may comprise: obtaining a first application type of a first application; further, according to the first application type, obtaining a first congestion parameter corresponding to the first application type, the first congestion parameter being used for obtaining a first congestion control algorithm, and the first congestion control algorithm being used for performing congestion control on traffic data of the first application.

Description

Congestion control method and corresponding device

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application with the application number 202010630381.7 and the application title "A Congestion Control Method and Corresponding Device" filed with the China Patent Office on June 30, 2020, the entire contents of which are incorporated herein by reference middle.

technical field

The present application relates to the technical field of computer networks, and in particular, to a congestion control method and corresponding device.

Background technique

Transmission Control Protocol (TCP), as the most widely used transmission protocol in the network, can provide connection-oriented and reliable data transmission services, and the TCP congestion control mechanism is the core of TCP.

The currently widely used TCP congestion control algorithm still uses a relatively fixed window adjustment strategy. However, because different services have different requirements on transmission performance indicators, for example, some applications have higher requirements on transmission performance indicators, while some applications have lower requirements on transmission performance indicators, when the TCP congestion control algorithm uses a relatively fixed window adjustment strategy , it is impossible to adaptively adjust the congestion parameters according to the dynamically changing network services, it is difficult to meet the respective requirements of different applications for transmission performance indicators, and it is impossible to effectively control the congestion of the traffic data of different applications, which will affect the user experience and cause inevitable consequences. waste of network resources.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a congestion control method and a corresponding device, which are used to effectively perform congestion control on traffic data of different applications, which can improve the utilization rate of network bandwidth resources without affecting the user experience of using applications.

In a first aspect, an embodiment of the present application provides a congestion control method, the method includes: obtaining a first application type of a first application; further, according to the first application type, obtaining a corresponding a first congestion parameter, where the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control algorithm is used to perform congestion control on the traffic data of the first application.

With the above design, since the first congestion parameter is determined based on the first application type of the first application, it can be ensured that the first congestion control algorithm obtained based on the first congestion parameter is suitable for the traffic of the first application Congestion control is performed on the data, so that the traffic data of the first application can be effectively controlled. Furthermore, limited network bandwidth resources can be allocated on the basis of not affecting the user's experience of using the first application, which can improve network performance. Utilization of bandwidth resources.

In a possible design, after acquiring the first congestion parameter corresponding to the first application type according to the first application type, the method further includes: acquiring the first congestion control algorithm based on the first congestion parameter; Congestion control is performed on the traffic data of the first application based on the first congestion control algorithm.

In a possible design, after performing congestion control on the traffic data of the first application based on the first congestion control algorithm, the method further includes: acquiring the traffic of the first application based on the first congestion control algorithm The first transmission performance index corresponding to the data when congestion control is performed; the first congestion parameter is adjusted according to the first transmission performance index.

With the above design, by adjusting the first congestion parameter corresponding to the first application type based on the first transmission performance index corresponding to the traffic data of the first application, it is possible to effectively control the congestion of the first application in different network environments, and further Yes, the limited network bandwidth resources can be allocated without affecting the user's experience of using the first application, which can improve the utilization rate of the network bandwidth resources.

In a possible design, adjusting the first congestion parameter according to the first transmission performance index includes: obtaining, according to the first transmission performance index, a requirement of the first application for the transmission performance index; The first congestion parameter is adjusted according to the requirements of the first application for transmission performance indicators.

With the above design, since the first congestion parameter corresponding to the first application type is adjusted based on the requirements of the first application on the transmission performance index, the adjusted first congestion control obtained based on the adjusted first congestion parameter When the algorithm performs congestion control on the traffic data of the first application, it can meet the requirements of the first application for transmission performance indicators, so that it can effectively perform congestion control on the traffic data of the first application. Based on the experience of an application, allocating limited network bandwidth resources can improve the utilization rate of network bandwidth resources.

In a possible design, adjusting the first congestion parameter according to the requirements of the first application on the transmission performance index includes: inputting the first transmission performance index into an objective function to obtain a first evaluation value; The objective function is used to evaluate the requirements of the first application on the transmission performance index; based on the first evaluation value, the first congestion parameter is adjusted.

With the above design, since the objective function can be used to evaluate the requirements of the first application on the transmission performance index, when the first congestion parameter corresponding to the first application type is adjusted based on the objective function and the first transmission performance index, the adjusted When the adjusted first congestion control algorithm obtained from the first congestion parameter of the first application performs congestion control on the traffic data of the first application, it can meet the requirements of the first application for transmission performance indicators, so that the traffic of the first application can be effectively controlled. Data congestion control is performed, and further, limited network bandwidth resources can be allocated without affecting the user's experience of using the first application, which can improve the utilization rate of network bandwidth resources.

In a possible design, the first transmission performance indicator may include at least two performance indicators, such as throughput and delay; the first application may perform at least one of the at least two performance indicators. When the index is of high requirement, the first congestion parameter may be adjusted in the following manner: adjusting the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions to obtain the adjusted first congestion parameter; The first congestion parameter obtains the adjusted first congestion control algorithm; performs congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm, and obtains the first congestion control algorithm based on the adjusted first congestion control algorithm. a second transmission performance index corresponding to the traffic data of the first application when congestion control is performed; inputting the second transmission performance index into the objective function to obtain a second evaluation value;

If the second evaluation value is greater than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return Adjusting the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions is performed to obtain the adjusted first congestion parameter; or,

If the second evaluation value is smaller than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, and adjust the first congestion parameter according to other adjustment directions among the plurality of adjustment directions. a congestion parameter to obtain a plurality of adjusted first congestion parameters, and the other adjustment directions are adjustment directions other than the first adjustment direction among the plurality of adjustment directions; based on the plurality of adjusted first congestion parameters parameters, respectively return to execute the adjusted first congestion control algorithm based on the adjusted first congestion parameters, until multiple second evaluation values are obtained; when at least one of the multiple second evaluation values is greater than When the first evaluation value is used, the first adjustment direction is replaced with the adjustment direction corresponding to the largest second evaluation value in the at least one second evaluation value, and the first evaluation value is replaced by the largest second evaluation value. For the second evaluation value, return to adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions, and obtain the adjusted first congestion parameter; when the plurality of second evaluation values are all smaller than the first adjustment direction When the evaluation value is obtained, the first evaluation value is determined as the maximum evaluation value of the objective function, and the first congestion parameter currently corresponding to the first evaluation value is used as the final first congestion parameter.

With the above design, since the first congestion parameter corresponding to the first application type of the first application is obtained through reinforcement learning, based on the requirements of the first application for transmission performance indicators and the traffic data of the first application, it can be guaranteed that The first congestion control algorithm obtained based on the first congestion parameter is suitable for performing congestion control on the traffic data of the first application, and can effectively perform congestion control on the traffic data of the first application. Based on the experience of the first application, allocating limited network bandwidth resources can improve the utilization rate of network bandwidth resources.

In a possible design, the transmission performance indicator may include at least two performance indicators, such as throughput rate and delay; when the first application has low requirements for the at least two performance indicators, it may include Adjusting the first congestion parameter in the following manner includes: adjusting the first congestion parameter according to a first adjustment direction among a plurality of adjustment directions to obtain an adjusted first congestion parameter; obtaining an adjustment based on the adjusted first congestion parameter performing congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm, and obtaining the traffic data of the first application based on the adjusted first congestion control algorithm a second transmission performance index corresponding to the congestion control; inputting the second transmission performance index into the objective function to obtain a second evaluation value;

If the second evaluation value is smaller than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return Adjusting the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions is performed to obtain the adjusted first congestion parameter; or,

If the second evaluation value is greater than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, and adjust the first congestion parameter according to other adjustment directions among the plurality of adjustment directions. a congestion parameter to obtain a plurality of adjusted first congestion parameters, and the other adjustment directions are adjustment directions other than the first adjustment direction among the plurality of adjustment directions; based on the plurality of adjusted first congestion parameters parameters, respectively return to execute the adjusted first congestion control algorithm based on the adjusted first congestion parameters, until multiple second evaluation values are obtained; when at least one of the multiple second evaluation values is less than In the case of the first evaluation value, the first adjustment direction is replaced with the adjustment direction corresponding to the smallest second evaluation value among the at least one second evaluation value, and the first evaluation value is replaced by the smallest second evaluation value. For the second evaluation value, return to adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions, and obtain the adjusted first congestion parameter; when the plurality of second evaluation values are all greater than the first adjustment direction When the evaluation value is obtained, the first evaluation value is determined as the minimum evaluation value of the objective function, and the first congestion parameter currently corresponding to the first evaluation value is used as the final first congestion parameter.

In a possible design, the first congestion parameter may include at least a first sub-parameter and a second sub-parameter; the multiple adjustment directions may include the following four adjustment directions, and the first adjustment direction may be the following Any one of four adjustment directions: increase the first sub-parameter and the second sub-parameter; increase the first sub-parameter, decrease the second sub-parameter; decrease the first sub-parameter sub-parameter, increase the second sub-parameter; decrease the first sub-parameter and the second sub-parameter.

In a possible design, the first congestion control algorithm includes a window-up algorithm and a window-down algorithm, the first sub-parameter is a parameter corresponding to the window-up algorithm, and the second sub-parameter is the window-down algorithm The parameters corresponding to the window algorithm. Specifically, the window raising algorithm is characterized as:

The window reduction algorithm is characterized as:

cwnd=cwnd(1-β)

Wherein, cwnd is used to represent the congestion window value, α is the first sub-parameter, and β is the second sub-parameter.

In a possible design, acquiring the first congestion parameter corresponding to the first application type according to the first application type includes: acquiring a mapping relationship between the application type and the congestion parameter; based on the mapping relationship and For the first application type, obtain a first congestion parameter corresponding to the first application type. Wherein, the mapping relationship may be stored in, but not limited to, a local storage of the network device, an external storage connected to the network device, and the cloud.

In a possible design, the mapping relationship may include multiple application types and congestion parameters corresponding to the multiple application types; for any application type in at least one application type in the mapping relationship, the The congestion parameter corresponding to the application type is determined in the following manner: obtaining the initial congestion parameter corresponding to the application type, and obtaining the initial congestion control algorithm corresponding to the application type based on the initial congestion parameter corresponding to the application type; The initial congestion control algorithm corresponding to the type, performs congestion control on the traffic data of at least one application corresponding to the application type, and obtains the initial transmission performance index corresponding to the at least one application; The performance indicator is input into an objective function to obtain at least one initial evaluation value, and the objective function is used to evaluate the respective requirements of the at least one application for the transmission performance indicator; a reinforcement learning method is adopted based on the at least one initial evaluation value and the at least one The respective traffic data is used for training to obtain the congestion parameter corresponding to the application type.

In a possible design, acquiring the first congestion parameter corresponding to the first application type based on the mapping relationship and the first application type includes: if the mapping relationship does not include the first application type, obtain the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship; or, if the mapping relationship includes the first application type, the first congestion parameter corresponding to the first application type is acquired according to the first application type and the mapping relationship.

With the above design, the second congestion parameter corresponding to the second application type of the first application can be obtained through the mapping relationship, so that the first application of the first application can be obtained according to the second congestion parameter corresponding to the second application type of the first application type, thereby ensuring that the first congestion control algorithm obtained based on the first congestion parameter is suitable for performing congestion control on the traffic data of the first application.

In a possible design, acquiring the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship includes: according to the first application type the second application type to which the first application type belongs and the mapping relationship, obtain a second congestion parameter corresponding to the second application type to which the first application type belongs, and obtain a second congestion control algorithm based on the second congestion parameter; The third transmission performance index corresponding to when the second congestion control algorithm performs congestion control on the traffic data of the first application; the third performance index is input into an objective function to obtain a third evaluation value; the objective function is used to evaluate The requirements of the first application for transmission performance indicators; the reinforcement learning method is used to perform training based on the third evaluation value and the traffic data of the first application to obtain a first congestion parameter corresponding to the first application type.

With the above design, since the first congestion parameter corresponding to the first application type of the first application adopts the reinforcement learning method, training is performed based on the second congestion parameter corresponding to the second application type of the first application and the traffic data of the first application obtained, it can be guaranteed that the first congestion control algorithm obtained based on the first congestion parameter is suitable for performing congestion control on the traffic data of the first application.

In a possible design, after adjusting the first congestion parameter according to the first transmission performance index, the method further includes: updating the mapping relationship based on the adjusted first congestion parameter.

In a second aspect, an embodiment of the present application provides a congestion control method, the method includes: acquiring a first transmission performance indicator corresponding to the congestion control of traffic data of a first application based on a first congestion control algorithm; further, according to The first transmission performance indicator adjusts the first congestion parameter corresponding to the first application type of the first application, the adjusted first congestion parameter is used to obtain an adjusted first congestion control algorithm, and the adjusted first congestion The control algorithm is used to perform congestion control on the traffic data of the first application.

With the above design, since the first congestion parameter corresponding to the first application type is adjusted based on the first transmission performance index corresponding to the traffic data of the first application, the first application can be effectively congested under different network environments Control, further, on the basis of not affecting the user's experience of using the first application, the limited network bandwidth resources can be allocated, which can improve the utilization rate of the network bandwidth resources.

In a possible design, adjusting the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator includes: obtaining the first congestion parameter according to the first transmission performance indicator Applying requirements for transmission performance indicators; adjusting the first congestion parameter according to the requirements of the first application for transmission performance indicators.

In a possible design, the first congestion control algorithm may include a window-up algorithm and a window-down algorithm, the first sub-parameter may be a parameter corresponding to the window-up algorithm, and the second sub-parameter may be Parameters corresponding to the window reduction algorithm. Specifically, the window raising algorithm is characterized as:

The window reduction algorithm is characterized as:

cwnd=cwnd(1-β)

In a possible design, the first transmission performance indicator may include at least two performance indicators, such as throughput and delay; the first application may perform at least one of the at least two performance indicators. When the index is high, the first congestion parameter can be adjusted in the following manner:

Adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions to obtain the adjusted first congestion parameter; obtain the adjusted first congestion control algorithm based on the adjusted first congestion parameter; The first congestion control algorithm performs congestion control on the traffic data of the first application, and acquires a second transmission performance index corresponding to when the adjusted first congestion control algorithm performs congestion control on the traffic data of the first application; Inputting the second transmission performance index into the objective function to obtain a second evaluation value;

In a possible design, the transmission performance indicator may include at least two performance indicators, such as throughput rate and delay; when the first application has low requirements for the at least two performance indicators, it may include Adjusting the first congestion parameter in the following manner includes:

In a possible design, before adjusting the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, the method may further include: acquiring a mapping relationship between the application type and the congestion parameter ; based on the mapping relationship and the first application type, obtain a first congestion parameter corresponding to the first application type. Wherein, the mapping relationship may be stored in, but not limited to, the local memory of the adjustment device, an external memory connected to the adjustment device, other devices (eg, network devices) connected to the adjustment device, and the cloud.

In a possible design, acquiring the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship includes: according to the first application type the second application type to which the first application type belongs and the mapping relationship, obtain a second congestion parameter corresponding to the second application type to which the first application type belongs, and obtain a second congestion control algorithm based on the second congestion parameter; 2. The third transmission performance index corresponding to when the congestion control algorithm performs congestion control on the traffic data of the first application; the third performance index is input into an objective function to obtain a third evaluation value; the objective function is used to evaluate all The requirements of the first application on the transmission performance index; the reinforcement learning method is used to perform training based on the third evaluation value and the traffic data of the first application to obtain a first congestion parameter corresponding to the first application type.

In a third aspect, an embodiment of the present application provides a network device, including:

the obtaining unit, configured to obtain the first application type of the first application;

The processing unit is configured to obtain, according to the first application type, a first congestion parameter corresponding to the first application type, where the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control The algorithm is used to perform congestion control on the traffic data of the first application.

In a possible design, after the processing unit is configured to acquire the first congestion parameter corresponding to the first application type according to the first application type, the processing unit may be further configured to: acquire based on the first congestion parameter the first congestion control algorithm; and performing congestion control on the traffic data of the first application based on the first congestion control algorithm.

In a possible design, after the processing unit is configured to perform congestion control on the traffic data of the first application based on the first congestion control algorithm, the processing unit may be further configured to: obtain information based on the first congestion control algorithm The first transmission performance index corresponding to the congestion control is performed on the traffic data of the first application; and the first congestion parameter is adjusted according to the first transmission performance index.

In a possible design, when the processing unit is configured to adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, the processing unit may be specifically configured to: A transmission performance indicator, obtaining the requirements of the first application on the transmission performance indicators; adjusting the first congestion parameter according to the requirements of the first application on the transmission performance indicators.

In a possible design, the processing unit is configured to adjust the first congestion parameter according to the requirements of the first application on the transmission performance index, which may be specifically used to: input the first transmission performance index an objective function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index; based on the first evaluation value, the first congestion parameter is adjusted.

In a possible design, the first transmission performance indicator may include at least two performance indicators, such as throughput and delay; the first application may perform at least one of the at least two performance indicators. When the indicator is high demand, the processing unit may adjust the first congestion parameter in the following manner:

In a possible design, the transmission performance indicators may include at least two performance indicators, such as throughput and delay; when the first application has low requirements for the at least two performance indicators, all The processing unit may adjust the first congestion parameter in the following manner:

The window reduction algorithm is characterized as:

cwnd=cwnd(1-β)

In a possible design, when the processing unit is configured to obtain the first congestion parameter corresponding to the first application type according to the first application type, the processing unit may be configured to: obtain the difference between the application type and the congestion parameter. A mapping relationship; based on the mapping relationship and the first application type, obtain a first congestion parameter corresponding to the first application type. Wherein, the mapping relationship may be stored in, but not limited to, a local storage of the network device, an external storage connected to the network device, and the cloud.

In a possible design, the mapping relationship may include multiple application types and congestion parameters corresponding to the multiple application types; for any application type in at least one application type in the mapping relationship, the The processing unit may determine the congestion parameter corresponding to the application type in the following manner: acquiring the initial congestion parameter corresponding to the application type, and acquiring the initial congestion control algorithm corresponding to the application type based on the initial congestion parameter corresponding to the application type; Based on the initial congestion control algorithm corresponding to the application type, congestion control is performed on the traffic data of at least one application corresponding to the application type, and initial transmission performance indicators corresponding to the at least one application are obtained; The corresponding initial transmission performance index is input into the objective function, and at least one initial evaluation value is obtained, and the objective function is used to evaluate the respective requirements of the at least one application on the transmission performance index; the reinforcement learning method is adopted based on the at least one initial evaluation value and The at least one application is trained with respective traffic data to obtain a congestion parameter corresponding to the application type.

In a possible design, when the processing unit is configured to obtain the first congestion parameter corresponding to the first application type based on the mapping relationship and the first application type, the processing unit may be specifically configured to: if the If the mapping relationship does not include the first application type, then obtain the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship; or, if the If the mapping relationship includes the first application type, the first congestion parameter corresponding to the first application type is acquired according to the first application type and the mapping relationship.

In a possible design, when the processing unit is configured to acquire the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship, the processing unit may specifically is used for: obtaining a second congestion parameter corresponding to the second application type to which the first application type belongs, according to the second application type to which the first application type belongs and the mapping relationship, and obtaining based on the second congestion parameter a second congestion control algorithm; a third transmission performance index corresponding to when performing congestion control on the traffic data of the first application based on the second congestion control algorithm; inputting the third performance index into an objective function to obtain a third evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index; the reinforcement learning method is used to perform training based on the third evaluation value and the traffic data of the first application to obtain the first application The first congestion parameter corresponding to the type.

In a possible design, after the processing unit is configured to adjust the first congestion parameter according to the first transmission performance indicator, the processing unit may also be configured to: update the mapping based on the adjusted first congestion parameter relation.

For the beneficial effects of the third aspect and its possible designs, reference may be made to the foregoing descriptions of the beneficial effects of the methods described in the first aspect and any of its possible designs.

In a fourth aspect, an embodiment of the present application provides a network device, including:

the obtaining unit, configured to obtain the first transmission performance index corresponding to the congestion control of the traffic data of the first application based on the first congestion control algorithm;

The processing unit is configured to adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, and the adjusted first congestion parameter is used to obtain an adjusted first congestion control The adjusted first congestion control algorithm is used to perform congestion control on the traffic data of the first application.

In a possible design, when the processing unit is configured to adjust the first congestion parameter according to the requirements of the first application on the transmission performance indicator, it may be specifically configured to: input the first transmission performance indicator an objective function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index; based on the first evaluation value, the first congestion parameter is adjusted.

The window reduction algorithm is characterized as:

cwnd=cwnd(1-β)

In a possible design, the first congestion parameter includes at least a first sub-parameter and a second sub-parameter; the multiple adjustment directions include the following four adjustment directions, and the first adjustment direction is the following four adjustment directions any one of the directions: increase the first sub-parameter and the second sub-parameter; increase the first sub-parameter, decrease the second sub-parameter; decrease the first sub-parameter, Increase the second sub-parameter; decrease the first sub-parameter and the second sub-parameter.

In a possible design, before the processing unit is configured to adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, the processing unit may also be configured to: obtain the application type and A mapping relationship between congestion parameters; based on the mapping relationship and the first application type, obtain a first congestion parameter corresponding to the first application type. Wherein, the mapping relationship may be stored in, but not limited to, the local memory of the adjustment device, an external memory connected to the adjustment device, other devices (eg, network devices) connected to the adjustment device, and the cloud.

For the beneficial effects of the fourth aspect and its possible designs, reference may be made to the foregoing description of the beneficial effects of the methods described in the second aspect and any of its possible designs.

In a fifth aspect, an embodiment of the present application provides a network device, including: at least one processor and a memory; the memory stores one or more computer programs; when the one or more computer programs stored in the memory are stored by the at least one When executed by one processor, the network device is caused to execute the method involved in any one of the foregoing first aspects.

In a sixth aspect, an embodiment of the present application provides an adjustment device, comprising: at least one processor and a memory; the memory stores one or more computer programs; when the one or more computer programs stored in the memory are stored by the at least one When executed by one processor, the network device is caused to execute the method involved in any one of the foregoing second aspects.

In a seventh aspect, an embodiment of the present application provides a computer storage medium, where the computer-readable storage medium is used to store a computer program, and when the computer program runs on a computer, the computer is made to execute the first aspect or the first aspect above. The method involved in any one of the two aspects.

In an eighth aspect, an embodiment of the present application provides a network system, including: an adjustment device and a network device;

The adjustment device is configured to obtain a first transmission performance index corresponding to the traffic data of the first application; adjust the first congestion parameter corresponding to the application type of the first application according to the first transmission performance index; sending the first congestion parameter to the network device;

The network device is configured to obtain an adjusted first congestion control algorithm according to the adjusted first congestion parameter, and perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm.

In a possible design, before the adjustment device is configured to acquire the first transmission performance indicator corresponding to the traffic data of the first application, the network device is further configured to: acquire the first application type of the first application; obtaining the first congestion parameter according to the first application type; obtaining a first congestion control algorithm based on the first congestion parameter;

When the adjustment device is configured to acquire the first transmission performance index corresponding to the traffic data of the first application, it is specifically configured to: acquire the congestion of the traffic data of the first application by the network device based on the first congestion control algorithm The first transmission performance index corresponding to the control.

In a possible design, after the network device is configured to perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm, the adjustment device is further configured to: obtain the network device according to the adjustment The second transmission performance index corresponding to when the second congestion control algorithm performs congestion control on the traffic data of the first application.

In a ninth aspect, an embodiment of the present application provides a network system, characterized in that it includes: an identification device and a network device;

the identifying device, configured to identify the first application type of the first application; sending the first application type to the network device;

The network device is configured to obtain, according to the first application type, a first congestion parameter corresponding to the first application type, where the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control The algorithm is used to perform congestion control on the traffic data of the first application.

In a possible design, after obtaining the first congestion parameter corresponding to the first application type according to the first application type, the network device is further configured to: obtain the first congestion parameter based on the first congestion parameter. the first congestion control algorithm; and based on the first congestion control algorithm, congestion control is performed on the traffic data of the first application.

In a possible design, the network system further includes an adjustment device, and the adjustment device is used for:

Acquire a first transmission performance index corresponding to when the network device performs congestion control on the traffic data of the first application based on the first congestion control algorithm; adjust the corresponding first application type according to the first transmission performance index The first congestion parameter of ; send the adjusted first congestion parameter to the network device;

The network device is configured to: obtain an adjusted first congestion control algorithm according to the adjusted first congestion parameter, and perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm.

Description of drawings

FIG. 1 is a schematic diagram of the architecture of a network system provided by an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a network system provided by an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a network system provided by an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a network system provided by an embodiment of the present application;

FIG. 5 is a schematic flowchart of a congestion control method provided by an embodiment of the present application;

6 is a schematic diagram of a process for a network device to obtain a congestion parameter corresponding to an application type a according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a process for a network device to obtain a congestion parameter corresponding to an application type a according to an embodiment of the present application;

8 is a schematic diagram of a process for a network device to obtain a congestion parameter corresponding to an application type a according to an embodiment of the present application;

9 is a schematic diagram of a process for a network device to adjust a first congestion parameter corresponding to a first application type of a first application according to an embodiment of the present application;

10 is a schematic diagram of a process in which a network device adjusts a first congestion parameter corresponding to a first application type of a first application based on a first evaluation value according to an embodiment of the present application;

11 is a schematic diagram of a process in which a network device adjusts a first congestion parameter corresponding to a first application type of a first application based on a first evaluation value according to an embodiment of the present application;

12 is a schematic flowchart of a congestion control method provided by an embodiment of the present application;

FIG. 13 is a schematic structural diagram of a network device according to an embodiment of the present application;

14 is a schematic structural diagram of an adjustment device provided by an embodiment of the application;

FIG. 15 is a schematic structural diagram of a network device according to an embodiment of the present application;

FIG. 16 is a schematic structural diagram of an adjustment device provided by an embodiment of the present application.

detailed description

In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings in the embodiments of the present application.

Please refer to FIG. 1 , which is a schematic structural diagram of a network system according to an embodiment of the present application. Wherein, the network system may include at least one terminal 101 and a network device 102 .

It should be understood that the network system provided by the embodiments of the present application may be applicable to both a low frequency scenario (sub 6G) and a high frequency scenario (above 6G). Application scenarios of the network system provided by the embodiments of the present application include, but are not limited to, a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (wideband) system code division multiple access (WCDMA) system, general packet radio service (GPRS), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division dual time division duplex (TDD), universal mobile telecommunication system (UMTS), worldwide interoperability for microwave access (WiMAX) network system, future fifth generation (5th generation, 5G) system or a new radio (NR) network system, etc.

It should be understood that in this embodiment of the present application, the terminal 101 may be a device with a wireless transceiver function, and may be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; it may also be deployed on water (such as a ship, etc.); it may also be deployed In the air (eg in airplanes, balloons, satellites, etc.). The terminal 101 can communicate with one or more network devices 102 in one or more network systems, and receive network services provided by the network devices 102 . For example, the terminal 101 in this embodiment of the present application may be a mobile phone (or referred to as a "cellular" phone), a session initiation protocol (SIP) phone, or a wireless local loop (WLL) station , personal digital assistant (PDA), computer with mobile terminal, etc. The terminal 101 may also be a user equipment (user equipment, UE), a terminal (terminal), a mobile station (mobile station, MS), a mobile phone (mobile phone), a tablet computer (pad), a computer with a wireless transceiver function, a virtual reality ( virtual reality (VR) terminal, augmented reality (AR) terminal, wireless terminal in industrial control, wireless terminal in self driving, wireless terminal in remote medical , wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. The terminal 101 may also be a communication chip with a communication module.

It should be understood that in this embodiment of the present application, the network device 102 includes but is not limited to: an access network (access network, AN) device, a radio network controller (radio network controller, RNC), a node B (node B, NB), a base station Controller (base station controller, BSC), base transceiver station (base transceiver station, BTS), home base station (for example, home evolved nodeB, or home node B, HNB), baseband unit (baseBand unit, BBU), transmission point ( transmitting and receiving point, TRP), transmitting point (transmitting point, TP), mobile switching center, etc. Network equipment 102 may be used to interconvert received air frames and Internet Protocol (IP) packets, acting as a router between terminal 101 and the rest of the access network, which may include an IP network. The network device 102 may also coordinate attribute management for the air interface. For example, the network device 102 may include an evolved base station (NodeB or eNB or e-NodeB, evolutional Node B) in a long term evolution (long term evolution, LTE) system or an evolved LTE system (LTE-Advanced, LTE-A), Alternatively, it may also include the next generation node B (gNB) in the 5G NR system, or may also include the centralized unit (CU) in the cloud radio access network (CloudRAN) system. And distributed unit (distributed unit, DU) and so on. The network device 102 may also be an access point (access point, AP) such as a wireless AP, or a switch, or a firewall, etc. The embodiment of the present application does not limit the specific form of the network device 102 .

It should be understood that, in the embodiment of the present application, the terminal 101 and the network device 102 may communicate directly or communicate through forwarding by other devices, which is not specifically limited in the embodiment of the present application. in:

The terminal 101 is used for running the first application.

The network device 102 is configured to acquire a first application type of the first application; further, acquire a first congestion parameter corresponding to the first application type of the first application according to the first application type of the first application. The first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control algorithm is used to perform congestion control on the traffic data of the first application.

In this embodiment of the present application, by acquiring the first congestion parameter corresponding to the first application type of the first application, the network device can obtain a first congestion control algorithm suitable for performing congestion control on the traffic data of the first application, thereby effectively Congestion control is performed on the traffic data of the first application, and further, limited network bandwidth resources can be allocated on the basis of not affecting the user's experience of using the first application, and the utilization rate of network bandwidth resources can be improved.

As shown in FIG. 2 , it is a schematic diagram of the architecture of a network system provided in the implementation of the present application. Wherein, in addition to the at least one terminal 101 and the network device 102 shown in FIG. 1, the network system may also include a device 103 for adjusting the congestion parameter. For simplicity, the name of the device for adjusting the congestion parameter is used herein. It is an example of adjusting equipment. Among them, the adjustment device 103 can be used for:

Obtain a first transmission performance index corresponding to the congestion control of the traffic data of the first application based on the first congestion control algorithm; further, adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance index .

In addition, the adjustment device 103 can send the adjusted first congestion parameter to the network device 102 in addition to the above functions, so that the network device 102 can obtain the adjusted first congestion control based on the adjusted first congestion parameter The algorithm, based on the adjusted first congestion control algorithm, performs congestion control on the traffic data of the first application.

It should be noted that, the foregoing network device 102 and adjustment device 103 may be integrated on the same device, or may be two independent devices, which are not limited in this embodiment of the present application. Wherein, when the network device 102 and the adjustment device 103 are two independent devices, the adjustment device 103 may include, but is not limited to, any device having the function of adjusting the congestion parameter, such as a switch, a firewall, and the like. Alternatively, when the adjustment device 103 and the network device 102 are integrated on the same device, for example, when the adjustment device 103 is integrated on the network device 102, the adjustment device 103 may be a device installed on the network device 102 that can be used to adjust the congestion parameter A software program, or a hardware circuit or the like set on the network device 102 that can be used to adjust the congestion parameter, in this case, the network device 102 may have the function of adjusting the congestion parameter. The embodiment of the present application does not limit the specific form of the adjustment device 103 .

In the embodiment of the present application, the first congestion parameter corresponding to the first application is adjusted by the adjustment device according to the first transmission performance index corresponding to the congestion control of the traffic data of the first application based on the first congestion control algorithm, so that the network device It can effectively perform congestion control on the traffic data of the first application in different network environments, and further, on the basis of not affecting the user's experience of using the first application, limited network bandwidth resources can be allocated to improve network bandwidth resources. utilization rate.

As shown in FIG. 3 , it is a schematic diagram of the architecture of a network system provided in the implementation of the present application. Wherein, in addition to the at least one terminal 101 and the network device 102 shown in FIG. 1, the network system may also include a device 104 for identifying the application type of the application. For simplicity, the application type for identifying the application is used herein. The name of the device is to identify the device as an example. Wherein, the identification device 104 may be used to identify the first application type of the first application.

In addition, the identification device 104 can send the first application type to the network device 102 in addition to the above functions.

It should be noted that, the foregoing network device 102 and identification device 104 may be integrated on the same device, or may be two independent devices, which are not limited in this embodiment of the present application. Wherein, when the network device 102 and the identification device 104 are two independent devices, the identification device 104 may include, but is not limited to, any device having the function of identifying the application type of the application, such as a switch and a firewall. When the identification device 104 and the network device 102 are integrated on the same device, for example, when the identification device 104 is integrated on the network device 102, the identification device 104 may be an application type installed on the network device 102 that can be used to identify the application. A software program, or a hardware circuit or the like set on the network device 102 that can be used to identify the application type of the application, in this case, the network device 102 can have the function of identifying the application type of the application. The embodiment of the present application does not limit the specific form of the identification device 104 .

In the embodiment of the present application, the network device obtains the first congestion parameter corresponding to the first application type by identifying the first application type of the first application identified by the device, and further, can obtain traffic data suitable for the first application A first congestion control algorithm for congestion control, so that congestion control can be effectively performed on the traffic data of the first application, and further, limited network bandwidth resources can be allocated on the basis of not affecting the user's experience of using the first application , to improve the utilization of network bandwidth resources.

Taking FIG. 1-FIG. 3 applicable to the network system shown in FIG. 4 as an example, the network system shown in FIG. 4 may include at least one terminal 101 and network device 102 shown in FIG. 1-FIG. device 103 and identification device 104 shown in FIG. 4 . in:

The terminal 101 is used for running the first application.

The identification device 104 is configured to identify the first application type of the first application; further, send the first application type of the first application to the network device 102 .

The network device 102 is configured to acquire, according to the first application type of the first application; further, acquire the first congestion parameter corresponding to the first application type according to the first application type of the first application. The first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control algorithm is used to perform congestion control on the traffic data of the first application.

The adjustment device 103 is configured to obtain a first transmission performance index corresponding to the congestion control of the traffic data of the first application based on the first congestion control algorithm; further, adjust the first application type of the first application according to the first transmission performance index the corresponding first congestion parameter; sending the adjusted first congestion parameter to the network device 102 .

The network device 102 is further configured to obtain an adjusted first congestion control algorithm according to the adjusted first congestion parameter, and perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm.

It should be noted that at least two of the network device 102, the adjustment device 103, and the identification device 104 shown in FIG. 4 may be integrated on the same device, for example, the identification device 104 and/or the adjustment device 103 may be integrated in the network device 102, at this time, the network device 102 may have the function of identifying the application type of the application and/or adjusting the congestion parameter, or the identifying device 104 and the adjusting device 103 may be integrated on the same device, at this time, the device has the function of identifying the application. The type of application and the function to adjust the congestion parameters. Certainly, the network device 102 , the adjustment device 103 , and the identification device 104 shown in FIG. 4 may also be independent devices, which are not limited in this embodiment of the present application.

In the embodiment of the present application, the network device can obtain the first congestion parameter corresponding to the first application type by identifying the first application type of the first application by the identifying device. Further, the network device can also adjust the device according to the first congestion control algorithm based on The first transmission performance index corresponding to the traffic data of the first application when congestion control is performed, and the first congestion parameter corresponding to the first application is adjusted, so that the first congestion suitable for performing congestion control on the traffic data of the first application can be obtained. The control algorithm is used to effectively perform congestion control on the traffic data of the first application in different network environments. Further, on the basis of not affecting the user's experience of using the first application, limited network bandwidth resources can be allocated well, Improve the utilization of network bandwidth resources.

Various technical solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Before introducing the embodiments of the present application, some terms in the present application will be explained first, so as to facilitate the understanding of those skilled in the art.

1) The first application involved in the embodiments of the present application may be any software program (application, APP for short) installed in the terminal that can realize one or more specific functions by connecting to a network. Among them, the first application may be: a game application, such as King of Glory, Peace Hero, etc., or may also be a communication application, such as WeChat (WeChat), Tencent Chat Software (QQ), DingTalk, etc., or, you can also It is a short video application, such as Douyin short video, Kuaishou short video, etc., or it can also be an online video application, such as Youku, iQiyi, Tencent Video, etc., and it can also be a web application, such as Baidu, Sohu, etc. , it may also be a virtual reality (virtual reality, VR) application type, etc., which is not specifically limited in this embodiment of the present application.

2) The term "at least one" in the embodiments of the present application refers to one or more, and "a plurality" refers to two or more. "And/or", which describes the association relationship of the associated objects, indicates that there can be three kinds of relationships, for example, A and/or B, which can indicate: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A, B can be singular or plural. The character "/" generally indicates that the associated objects are an "or" relationship. The singular expressions "a", "an", "the", "above", "the" and "the" are intended to also include such expressions as "one or more" unless the context clearly dictates otherwise. to the contrary. And, unless stated to the contrary, the ordinal numbers such as “first” and “second” mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, sequence, priority or priority of multiple objects. Importance. For example, the first application and the second application are only used to distinguish different applications, but do not indicate the difference in priority or importance of the two applications.

In addition, it should be understood that references to "one embodiment" or "some embodiments" and the like described in the embodiments of the present application mean that specific features described in connection with the embodiments are included in one or more embodiments of the present application , structure or characteristics. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean "one or more but not all embodiments" unless specifically emphasized otherwise. The terms "including", "including", "having" and their variants mean "including but not limited to" unless specifically emphasized otherwise.

The congestion control method provided by the embodiment of the present application will be described in detail below with reference to FIGS. 1-4 .

In some embodiments, taking the network system shown in FIGS. 1-3 applied to the network system shown in FIG. 4 as an example, as shown in FIG. 5 , it is a schematic flowchart of a congestion control method provided by an embodiment of the present application . Wherein, the method flow includes the following steps:

S201. Acquire a first application type of a first application.

In some embodiments, when the terminal is connected to the network through the network device, the terminal can perform various learning or entertainment activities by using the network. For example, if the first application is an online video application, the terminal can play the video by using the network when running the first application, or, if the first application is a game application, the terminal can display the game operation screen by using the network when running the first application ,etc. In this process, the identification device may acquire the traffic data of the first application, and based on the traffic data of the first application, identify the first application type of the first application by using a corresponding identification method. As an example, the identification device may identify the first application type of the first application based on the traffic data of the first application by using a port number classification identification method. Alternatively, the identification device may identify the first application type of the first application by adopting a deep packet inspection (deep packet inspection, DPI) identification method based on the traffic data of the first application. Alternatively, the identification device may identify the first application type of the first application by adopting a deep flow inspection (deep flow inspection, DFI) identification method based on the flow data of the first application. Alternatively, the identification device may identify the first application type of the first application by using a machine learning identification method based on the traffic data of the first application, and so on. In a specific implementation process, the identification device may also identify the first application type of the first application based on the traffic data of the first application by combining the above identification methods, which is not specifically limited in this embodiment of the present application.

The first application type may also be referred to as a sub-type application type in this application. For example, if the first application is the King of Glory, the first application type of the first application may be the King of Glory application type.

In some embodiments, the identification device may send the identified first application type of the first application to the network device, and in addition, the identification device may also forward traffic data of the first application to the network device. Correspondingly, the network device may obtain the first application type of the first application sent by the identification device, and obtain the traffic data of the first application forwarded by the identification device.

In this embodiment of the present application, the network device can identify the first application type of different applications based on the respective traffic data of different applications by identifying the device, so that when the network device performs congestion control on the respective traffic data of different applications, it can be based on The respective first application types of different applications select appropriate congestion control algorithms for different applications, which are used to perform congestion control on the respective traffic data of different applications, so as to effectively perform congestion control on the respective traffic data of different applications, and further, can On the basis of not affecting the user's experience of using these applications, allocating limited network bandwidth resources can improve the utilization rate of network bandwidth resources.

S202. Acquire a first congestion parameter corresponding to the first application type according to the first application type, where the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control algorithm is used to The traffic data of the first application is used for congestion control.

In some embodiments, after obtaining the first congestion parameter corresponding to the first application type, the network device may obtain the first congestion control algorithm based on the first congestion parameter, and may perform the first congestion control algorithm on the traffic data of the first application based on the first congestion control algorithm. Congestion control is performed.

In this embodiment of the present application, since the first congestion parameter is determined based on the first application type of the first application, it can be ensured that the first congestion control algorithm obtained by the network device based on the first congestion parameter is suitable for The traffic data of the first application is subject to congestion control, so that congestion control can be effectively performed on the traffic data of the first application, and further, limited network bandwidth can be allocated on the basis of not affecting the user's experience of using the first application resources, which can improve the utilization of network bandwidth resources.

In some embodiments, the network device may acquire a pre-stored mapping relationship between application types and congestion parameters. Optionally, the mapping relationship may include multiple application types and respective congestion parameters corresponding to the multiple application types. The mapping relationship may be one or any combination of a network device stored in a local storage, an external storage connected to the network device, a cloud, and the like, which is not specifically limited in this embodiment of the present application. In a specific implementation process, the multiple application types included in the mapping relationship may include multiple second application types (this application may also be referred to as broad application types), and may also include at least one of the multiple second application types Each of the second application types includes at least one first application type, that is, the first application type belongs to the second application type. Specifically, the multiple second application types may include, but are not limited to: game application types, online video application types, short video application types, online music application types, VR application types, and web page application types, etc. This is not specifically limited in the application examples. As an example, taking a second application type among the plurality of second application types as an example of a game application type, the second application type may include the first application type such as the King of Glory application type or the Peace Hero application type.

In some embodiments, the above-mentioned first congestion parameter may be obtained by the network device based on the first application type of the first application and the mapping relationship.

In a specific implementation process, for any application type in at least one application type in the mapping relationship between the application type and the congestion parameter, for simplicity, the application type is called application type a as an example. Wherein, the application type a generally refers to the second application type. The congestion parameter corresponding to the application type a may be obtained by training the adjustment device based on the traffic data of at least one application corresponding to the application type a by using reinforcement learning. Specifically, when the adjustment device is integrated on the network device, the congestion parameter corresponding to the application type a may be obtained by the network device using reinforcement learning through training based on the traffic data of at least one application corresponding to the application type a. When the adjustment device and the network device are independent devices, the network device may acquire the congestion parameter corresponding to the application type a obtained by the adjustment device based on reinforcement learning training.

The following takes the example that the adjustment device is integrated on the network device, that is, the network device has the function of adjusting the congestion parameter.

Please refer to FIG. 6 , which is a schematic diagram of a process for a network device to obtain a congestion parameter corresponding to an application type a according to an embodiment of the present application. Wherein, FIG. 6 takes the execution subject as a network device as an example. As shown in Figure 6, the process may include the following steps:

S301. Obtain an initial congestion parameter corresponding to the application type a, and obtain an initial congestion control algorithm based on the initial congestion parameter.

In some embodiments, the congestion control algorithm may include, but is not limited to, the following two mechanisms: a congestion reduction window mechanism and a window recovery mechanism. Among them, in the congestion window mechanism and window recovery mechanism, the window raising algorithm can be characterized as:

The window reduction algorithm can be characterized as:

cwnd=cwnd(1-β)

Among them, in the above window up algorithm and window down algorithm, cwnd is used to represent the congestion window value, and α and β are coefficients, that is, congestion parameters. Among them, different values of α and β can correspond to different congestion control algorithms, and different congestion control algorithms also have different effects on the transmission performance index of the application.

In some embodiments, before training the traffic data of at least one application corresponding to the application type a, the network device may initialize the congestion parameter corresponding to the application type a to obtain the initial congestion parameter corresponding to the application type a. Specifically, the initial congestion parameter may include a first sub-parameter and a second sub-parameter. As an example, the first sub-parameter may be a parameter corresponding to the window-up algorithm, for example, the first sub-parameter may be α, and the second sub-parameter may be a parameter corresponding to the window-down algorithm, for example, the second sub-parameter may be β. The network device may initialize the first sub-parameter α in the congestion parameter corresponding to the application type a to 1, and the second sub-parameter β to 0.5, that is, obtain the first sub-parameter in the initial congestion parameter corresponding to the application type a as 1, The second subparameter is 0.5.

In some embodiments, the network device may obtain the initial congestion control algorithm corresponding to the application type a based on the initial congestion parameter corresponding to the application type a. For example, when the first sub-parameter α of the initial congestion parameters corresponding to the application type a is 1 and the second sub-parameter β is 0.5, the initial congestion control algorithm corresponding to the application type a may be an early reno algorithm.

S302. Based on the initial congestion control algorithm corresponding to the application type a, perform congestion control on the traffic data of at least one application corresponding to the application type a, and obtain the initial transmission performance index corresponding to the at least one application.

In some embodiments, the network device may perform congestion control on the traffic data of at least one application (hereinafter referred to as the at least one application) corresponding to the application type a based on the obtained initial congestion control algorithm corresponding to the application type a, to obtain Each corresponding initial transmission performance index of the at least one application. For example, when the initial congestion control algorithm corresponding to the application type a is an early reno algorithm, the network device may perform congestion control on the traffic data of the at least one application based on the reno algorithm, and obtain the initial transmission corresponding to the at least one application. Performance. Specifically, the network device may perform congestion control on the traffic data of the at least one application by using the above-mentioned window-up algorithm and the above-mentioned window-down algorithm. During this process, the network device may record the initial transmission performance index corresponding to the congestion control of the traffic data of the at least one application based on the initial congestion control algorithm corresponding to the application type a. In other words, the network device may obtain the corresponding initial transmission performance index based on the application type a. The initial congestion control algorithm corresponds to the initial transmission performance index when congestion control is performed on the traffic data of the at least one application.

S303. Input the respective initial transmission performance indicators corresponding to the at least one application into an objective function to obtain at least one initial evaluation value, where the objective function is used to evaluate the respective requirements of the at least one application for the transmission performance indicators.

In some embodiments, the network device may obtain an objective function, and the objective function may be used to evaluate the respective requirements of the at least one application on the transmission performance index. It can be understood that the objective function may be used to measure the initial congestion corresponding to the application type a The control algorithm, the effect of performing congestion control on the traffic data of the at least one application, is to measure whether the initial congestion control algorithm corresponding to the application type a can better meet the respective requirements of the at least one application for transmission performance indicators.

In this embodiment of the present application, since network bandwidth resources are limited, and applications of different application types have different requirements for transmission performance indicators, the network device can obtain the objective function to measure whether the initial congestion control algorithm corresponding to application type a can be better The respective requirements of the at least one application on the transmission performance index are met, so that the respective requirements of the at least one application on the transmission performance index can be met.

In some embodiments, the transmission performance indicators may include at least two performance indicators. Applications of different application types have different requirements for transmission performance indicators. It can be understood that applications of different application types may have different performance indicators for at least two performance indicators. Require. For example, applications of some application types have high requirements on at least one performance index of at least two performance indicators, and other applications have low requirements on at least two performance indicators, and so on.

As an example, the at least two performance indicators may include latency and throughput. Applications of different application types can have different requirements for throughput and latency. For example, if the application type a is a game application type, since the delay has a greater impact on the game application, and the throughput rate has a small impact on the game application, the network device can determine the impact of the at least one application on the delay based on the application type a. For high requirements, low throughput requirements. Alternatively, if the application type a is a VR application type, since both the delay and the throughput rate have a great impact on the VR type application, the network device can apply the type a to determine that the at least one application has high requirements on the throughput rate and delay. Alternatively, if the application type a is an online video application type, since the delay has little impact on the online video application and the throughput rate has a greater impact on the online video application, the network device can determine the at least one application based on the application type a. The throughput rate is high, and the delay is low. Alternatively, if the application type a is a web page application type, since the delay and throughput rate have little impact on the web page application, the network device may determine, based on the application type a, that the at least one application has low requirements for the throughput rate and the delay. ,etc. Wherein, the at least one application has high requirements on throughput rate and/or delay, which may be understood as the traffic data of the at least one application requires low delay and/or high throughput rate, and the at least one application has high requirements on throughput rate and/or high throughput rate. The latency is a low requirement, which can be understood as requiring high latency and low throughput for the traffic data of the at least one second application.

As an example, when the at least two transmission performance indicators include throughput and delay, the objective function can be characterized as:

R(x,y)=η*U(x)+(1-η)*U(y)

Wherein, x represents the inverse of the delay corresponding to the traffic data of the at least one application based on the initial congestion control algorithm, and y represents the congestion control of the traffic data of the at least one application based on the initial congestion control algorithm. is the corresponding throughput rate, η represents the balance parameter of the corresponding throughput rate and delay when performing congestion control on the traffic data of the at least one application based on the initial congestion control algorithm, and U(x) is used to indicate that x is normalized Value, U(y) is used to indicate the normalized value of y.

In a specific implementation process, after acquiring the initial transmission performance index corresponding to the at least one application, the network device can input the initial transmission performance index corresponding to the at least one application into the objective function to obtain at least one initial evaluation value .

S304. Use reinforcement learning to perform training based on the at least one initial evaluation value and the respective traffic data of the at least one application, to obtain a congestion parameter corresponding to the application type a.

In some embodiments, after obtaining the at least one initial evaluation value, the network device may use reinforcement learning to perform training based on the at least one initial evaluation value and the respective traffic data of the at least one application to obtain the congestion parameter corresponding to the application type a.

For example, after obtaining at least one initial evaluation value, the network device may adjust the initial congestion parameter corresponding to the application type a to obtain the adjusted initial congestion control algorithm. The network device may perform congestion control on the traffic data of the at least one application based on the adjusted initial congestion control algorithm, and obtain a fourth corresponding to when performing congestion control on the traffic data of the at least one application based on the adjusted initial congestion control algorithm. transmission performance index, and at least one fourth evaluation value of the objective function can be obtained based on the fourth transmission performance index. The network device can adjust the initial congestion corresponding to the application type a according to the corresponding adjustment method by judging the magnitude relationship between the at least one fourth evaluation value and the at least one initial evaluation value, and the respective requirements of the at least one application for the transmission performance index. parameter, obtain the maximum evaluation value or the minimum evaluation value of the objective function, and obtain the congestion parameter corresponding to the application type a.

Exemplarily, taking the second application in the at least one application as an example, the network device may apply the initial congestion parameter corresponding to type a to obtain an adjusted initial congestion control algorithm, and may obtain an initial congestion control algorithm based on the adjusted initial congestion control algorithm. The fourth transmission performance index corresponding to the congestion control of the traffic data of the second application. The network device inputs the fourth transmission performance index into the objective function, and can obtain a fourth evaluation value of the objective function. After that, the network device can adjust the initial congestion corresponding to the application type a according to the corresponding adjustment method by judging the magnitude relationship between the fourth evaluation value and the initial evaluation value corresponding to the application type a and the requirements of the second application on the transmission performance index parameter, obtain the maximum evaluation value or the minimum evaluation value of the objective function, and obtain the congestion parameter corresponding to the application type a.

The following describes in detail the process of obtaining the congestion parameter corresponding to the training application type a by training the network device using the reinforcement learning method corresponding to the initial evaluation value corresponding to the application type a and the traffic data of the second application with reference to Figures 5-8.

In some embodiments, the network device may acquire the requirements of the second application for the transmission performance index based on the fourth transmission performance index of the second application. For example, the network device may obtain the requirements of the second application on the transmission performance index by analyzing the fourth transmission performance index. Alternatively, the network device may determine, based on the application type a, the second application's requirement on the transmission performance indicator, which is not limited in this embodiment of the present application. After the network device determines the requirements of the second application for the transmission performance indicators, it can use the corresponding reinforcement learning method to perform training based on the initial evaluation value corresponding to the application type a and the traffic data of the second application, and obtain the congestion parameter corresponding to the training application type a. .

Exemplarily, as shown in FIG. 7 , it is a schematic diagram of a process for a network device to acquire a congestion parameter corresponding to an application type a according to an embodiment of the present application. In FIG. 7 , the execution subject is the network device, and the second application has a high requirement on at least one of the at least two performance indicators included in the transmission performance indicator as an example. As shown in Figure 7, the process may include the following steps:

S401. Obtain an initial congestion parameter corresponding to the application type a, and obtain an initial evaluation value corresponding to the application type a based on the initial congestion parameter corresponding to the application type a.

In the specific implementation process, the initial evaluation value corresponding to the network device application type a in step S401 is similar to that obtained by the network device shown in FIG. 6 to obtain at least one initial evaluation value. This will not be repeated here.

S402. Adjust the initial congestion parameter corresponding to the application type a according to the first adjustment direction among the plurality of adjustment directions, to obtain the adjusted initial congestion parameter.

Specifically, the multiple adjustment directions may include four adjustment directions, for example, including increasing the first sub-parameter and the second sub-parameter in the initial congestion parameter corresponding to the application type a, and increasing the initial congestion parameter corresponding to the application type a. For the first sub-parameter, decrease the second sub-parameter in the initial congestion parameter corresponding to application type a, or decrease the first sub-parameter in the initial congestion parameter corresponding to application type a, and increase the initial congestion parameter corresponding to application type a The second sub-parameter in the parameter, or the first sub-parameter and the second sub-parameter in the initial congestion parameter corresponding to the application type a are reduced.

S403. Obtain an adjusted initial congestion control algorithm based on the adjusted initial congestion parameter.

In a specific implementation process, after obtaining the adjusted initial congestion parameters, the network device can obtain the adjusted initial congestion control algorithm based on the window raising algorithm and the window lowering algorithm in S301 above, which will not be repeated here.

S404 , perform congestion control on the traffic data of the second application based on the adjusted initial congestion control algorithm, and obtain a fourth transmission performance index corresponding to the time when congestion control is performed on the traffic data of the second application based on the adjusted initial congestion control algorithm.

S405. Input the fourth transmission performance index into the objective function to obtain a fourth evaluation value.

S406. Determine whether the fourth evaluation value is greater than the initial evaluation value corresponding to the application type a. If yes, execute S407, otherwise, execute S408.

S407. Replace the initial congestion parameter with the adjusted initial congestion parameter, replace the initial evaluation value corresponding to the application type a with the fourth evaluation value, and return to S402.

S408. Replace the initial congestion parameter with the adjusted initial congestion parameter, adjust the initial congestion parameter according to other adjustment directions among the multiple adjustment directions, and obtain multiple adjusted initial congestion parameters, and the other adjustment directions are among the multiple adjustment directions. Adjustment directions other than the first adjustment direction; based on the plurality of adjusted initial congestion parameters, return to execute S403-S405 respectively, obtain a plurality of fourth evaluation values, and then execute S409.

S409: Determine whether there is at least one fourth evaluation value in the plurality of fourth evaluation values that is greater than the initial evaluation value corresponding to the application type a. If it exists, execute S410, otherwise, execute S411.

S410. Replace the first adjustment direction with the adjustment direction corresponding to the largest fourth evaluation value among the at least one fourth evaluation value, replace the evaluation value corresponding to the application type a with the largest fourth evaluation value, and return to executing S402.

S411. Determine the initial evaluation value corresponding to the application type a is the maximum evaluation value of the objective function, and use the initial congestion parameter currently corresponding to the initial evaluation value corresponding to the application type a as the final congestion parameter corresponding to the application type a.

Exemplarily, as shown in FIG. 8 , it is a schematic diagram of a process for a network device to acquire a congestion parameter corresponding to an application type a according to an embodiment of the present application. Wherein, FIG. 8 takes the execution subject as the network device, and takes as an example that the second application has low requirements for at least two performance indicators included in the transmission performance indicator. As shown in Figure 8, the process may include the following steps:

S501. Obtain an initial congestion parameter corresponding to the application type a, and obtain an initial evaluation value corresponding to the application type a based on the initial congestion parameter corresponding to the application type a.

S502. Adjust the initial congestion parameter corresponding to the application type a according to the first adjustment direction among the plurality of adjustment directions, to obtain the adjusted initial congestion parameter.

S503. Obtain an adjusted initial congestion control algorithm based on the adjusted initial congestion parameter.

S504. Perform congestion control on the traffic data of the second application based on the adjusted initial congestion control algorithm, and obtain a fourth transmission performance index corresponding to the congestion control on the traffic data of the second application based on the adjusted initial congestion control algorithm.

S505. Input the fourth transmission performance index into the objective function to obtain a fourth evaluation value.

In a specific implementation process, steps S501-S505 are similar to steps S401-S405 shown in FIG. 7 above. For details, reference may be made to the relevant descriptions of the above-mentioned S401-S405, which will not be repeated here.

S506. Determine whether the fourth evaluation value is smaller than the initial evaluation value corresponding to the application type a. If yes, execute S507, otherwise, execute S508.

S507. Replace the initial congestion parameter with the adjusted initial congestion parameter, replace the initial evaluation value corresponding to the application type a with the fourth evaluation value, and return to S502.

S508. Replace the initial congestion parameters with the adjusted initial congestion parameters, adjust the initial congestion parameters according to other adjustment directions in the multiple adjustment directions, and obtain multiple adjusted initial congestion parameters; based on the multiple adjusted initial congestion parameters , respectively return to execute S503-S505, obtain a plurality of fourth evaluation values, and then execute S509.

S509: Determine whether there is at least one fourth evaluation value in the plurality of fourth evaluation values that is smaller than the initial evaluation value corresponding to the application type a. If it exists, execute S510, otherwise, execute S511.

S510. Replace the first adjustment direction with the adjustment direction corresponding to the smallest fourth evaluation value among the at least one fourth evaluation value, replace the initial evaluation value corresponding to the application type a with the smallest fourth evaluation value, and return to executing S502.

S511. Determine the initial evaluation value corresponding to the application type a is the minimum evaluation value of the objective function, and use the initial congestion parameter currently corresponding to the initial evaluation value corresponding to the application type a as the final congestion parameter corresponding to the application type a.

Wherein, since the application type a may correspond to at least one application, when the at least one application includes multiple applications, the network device may select an application among the multiple applications, and obtain the application in the manner shown in FIG. 7 or FIG. 8 . Congestion parameter corresponding to type a. Alternatively, since different applications may have small differences in transmission performance indicators, the network device may obtain multiple congestion parameters corresponding to application type a in the manner shown in FIG. 7 or FIG. 8 based on multiple applications. The final congestion parameter corresponding to the application type a can be obtained in the following way. For example, the average value of multiple congestion parameters corresponding to the application type a can be taken as the final congestion parameter corresponding to the application type a.

It should be noted that the congestion parameter corresponding to the application type a in the above-mentioned mapping relationship may be obtained by training the network device offline through the test network in the manner shown in FIG. 7 or FIG. 8 .

It should be noted that the above is an example of the first application type including the first application in the mapping relationship between the application type and the congestion parameter. In a specific implementation process, when the mapping relationship between the application type and the congestion parameter does not include the first application type of the first application, the network device may determine, according to the second application type and the mapping relationship to which the first application type belongs, to determine The first congestion parameter corresponding to the first application type. Afterwards, the network device may update the mapping relationship according to the first congestion parameter corresponding to the first application type of the first application. For example, taking the first application as the King of Glory as an example, when the mapping relationship only includes the game application type, that is, the King of Glory application type is not included, the network device can determine the King of Glory application type according to the game application type and the mapping relationship. The corresponding first congestion parameter.

The following specifically describes the process of acquiring the first congestion parameter corresponding to the first application type of the first application by the network device according to the second application type of the first application and the mapping relationship between the application type and the congestion parameter.

In some embodiments, after acquiring the first application type of the first application, the network device may determine the second application type of the first application according to the first application type of the first application. Afterwards, the network device may acquire the second congestion parameter corresponding to the second application type of the first application according to the second application type of the first application and the mapping relationship. At this time, the second congestion parameter corresponding to the second application type of the first application obtained by the network device can be understood as initializing the value of the first congestion parameter corresponding to the first application type of the first application, that is, the mapping The value of the second congestion parameter corresponding to the second application type of the first application included in the relationship is the initial value of the first congestion parameter corresponding to the first application type of the first application. After that, the network device may use reinforcement learning to perform training based on the second congestion parameter corresponding to the second application type of the first application and the traffic data of the first application to obtain the first congestion parameter corresponding to the first application type of the first application parameter. For example, the network device may obtain the second congestion control algorithm based on the second congestion parameter corresponding to the second application type of the first application, and may obtain the second congestion control algorithm corresponding to the congestion control of the traffic data of the first application based on the second congestion control algorithm. Three transmission performance indicators, the third transmission performance indicator may be input into the objective function to obtain a third evaluation value. Afterwards, the network device may perform training based on the third evaluation value and the traffic data of the first application in a reinforcement learning manner to obtain a first congestion parameter corresponding to the first application type of the first application. For the specific training process, reference may be made to the related descriptions of steps S401-S411 shown in FIG. 7 or steps S501-S511 shown in FIG. 8 , which will not be repeated here.

It should be noted that when the mapping relationship between the application type and the congestion parameter does not include the first application type and the second application type of the first application, the network device can obtain the first application type as shown in FIG. 7 or FIG. 8 . For the first congestion parameter corresponding to the first application type of an application and/or the second congestion parameter corresponding to the second application type, please refer to steps S401-S411 shown in FIG. 7 or steps S501-S511 shown in FIG. 8 for details. The related descriptions are not repeated here.

It should be noted that when the mapping relationship between the application type and the congestion parameter does not include the first congestion parameter corresponding to the first application type of the first application, the first congestion parameter corresponding to the first application type of the first application may be It is obtained by training the network equipment online in the manner shown in FIG. 7 or FIG. 8 , that is, the network equipment is trained in the manner shown in FIG. 7 or FIG. 8 when the first application is used.

In the embodiment of the present application, since the first congestion parameter corresponding to the first application type of the first application is the network device using the reinforcement learning method to perform training based on the first application's requirements for transmission performance indicators and the traffic data of the first application obtained, it can be ensured that the first congestion control algorithm obtained by the network device based on the first congestion parameter is suitable for performing congestion control on the traffic data of the first application, and can effectively perform congestion control on the traffic data of the first application, and further , the limited network bandwidth resources can be allocated on the basis of not affecting the user's experience of using the first application, and the utilization rate of the network bandwidth resources can be improved.

In this embodiment of the present application, since the network environment may change, during the process of running the first application on the terminal, the network device may adjust the first congestion parameter corresponding to the first application type of the first application to apply to different network environments, Therefore, the limited network bandwidth resources can be allocated without affecting the user's experience of using the first application, and the utilization rate of the network bandwidth resources can be improved.

The specific process of adjusting the first congestion parameter corresponding to the first application type of the first application by the network device will be described below with reference to FIGS. 5-9 .

Please refer to FIG. 9 , which is a schematic diagram of a process for a network device to adjust a first congestion parameter corresponding to a first application type of a first application according to an embodiment of the present application. Wherein, FIG. 9 takes the execution subject as a network device as an example. As shown in Figure 9, the process may include the following steps:

S601. Acquire a first transmission performance indicator corresponding to when congestion control is performed on the traffic data of the first application based on the first congestion control algorithm.

In some embodiments, when the network device performs congestion control on the traffic data of the first application based on the first congestion control algorithm, the network device may obtain the corresponding information when performing congestion control on the traffic data of the first application based on the first congestion control algorithm. The first transmission performance index. For the specific process, reference may be made to the relevant descriptions of steps S301-S302 shown in FIG. 6 above, which will not be repeated here.

S602. Adjust the first congestion parameter according to the first transmission performance indicator.

In some embodiments, the network device may acquire the requirements of the first application for the transmission performance index according to the first transmission performance index. For example, the network device may obtain the requirements of the first application for the transmission performance indicator by analyzing the first transmission performance indicator. Alternatively, the network device may determine, based on the first application type of the first application, the requirement of the first application on the transmission performance indicator, which is not limited in this embodiment of the present application. Afterwards, the network device may adjust the first congestion parameter corresponding to the first application type of the first application based on the first application's requirement for the transmission performance indicator. For example, the network device can evaluate the requirements of the first application on the transmission performance index by acquiring the objective function. In other words, the objective function can be used to measure the effect of the first congestion control algorithm on the congestion control of the traffic data of the first application, that is, to measure whether the first congestion control algorithm can meet the requirements of the first application for transmission performance indicators. Afterwards, the network device may input the first transmission performance index into the objective function to obtain the first evaluation value. Afterwards, the network device may adjust the first congestion parameter based on the first evaluation value.

The following specifically describes the process of the network device adjusting the first congestion parameter corresponding to the first application type of the first application based on the first evaluation value with reference to FIGS. 5-10 .

Exemplarily, as shown in FIG. 10 , a schematic diagram of a process in which a network device adjusts a first congestion parameter corresponding to a first application type of a first application based on a first evaluation value according to an embodiment of the present application. In FIG. 10 , the execution subject is the network device, and the first application has a high requirement on at least one performance indicator of the at least two performance indicators included in the transmission performance indicator as an example. As shown in Figure 10, the process may include the following steps:

S701. Adjust an initial congestion parameter corresponding to a first application type of a first application according to a first adjustment direction among a plurality of adjustment directions, to obtain an adjusted first congestion parameter.

S702. Obtain an adjusted first congestion control algorithm based on the adjusted first congestion parameter.

S703. Perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm, and obtain a second transmission performance corresponding to the time when the traffic data of the first application is congestion controlled based on the adjusted first congestion control algorithm index.

S704. Input the second transmission performance index into the objective function to obtain a second evaluation value.

S705. Determine whether the second evaluation value is greater than the first evaluation value. If yes, execute S706, otherwise, execute S707.

S706: Replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return to S701.

S707. Replace the first congestion parameter with the adjusted first congestion parameter, adjust the first congestion parameter according to other adjustment directions in the multiple adjustment directions, and obtain a plurality of adjusted first congestion parameters, and the other adjustment directions are multiple An adjustment direction other than the first adjustment direction among the adjustment directions; based on the plurality of adjusted first congestion parameters, return to execute S702-S704 respectively, obtain a plurality of second evaluation values, and then execute S708.

S708. Determine whether at least one second evaluation value is greater than the first evaluation value among the plurality of second evaluation values. If it exists, execute S709, otherwise, execute S710.

S709: Replace the first adjustment direction with an adjustment direction corresponding to the largest second evaluation value among the at least one second evaluation value, replace the first evaluation value with the largest second evaluation value, and return to executing S701.

S710. Determine the first evaluation value as the maximum evaluation value of the objective function, and use the first congestion parameter currently corresponding to the first evaluation value as the first congestion parameter finally corresponding to the first application type of the first application.

Wherein, steps S701 to S710 are similar to steps S402 to S411 shown in FIG. 7 above, and the specific process can refer to the relevant descriptions of the above steps S402 to S411, which will not be repeated here.

Exemplarily, as shown in FIG. 11 , a schematic diagram of a process in which a network device adjusts a first congestion parameter corresponding to a first application type of a first application based on a first evaluation value according to an embodiment of the present application. In FIG. 11 , the execution subject is the network device, and it is taken as an example that the first application has low requirements for at least two performance indicators included in the transmission performance indicator. As shown in Figure 11, the process may include the following steps:

S801. Adjust an initial congestion parameter corresponding to a first application type of a first application according to a first adjustment direction among a plurality of adjustment directions, to obtain an adjusted first congestion parameter.

S802. Obtain an adjusted first congestion control algorithm based on the adjusted first congestion parameter.

S803. Perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm, and acquire a second transmission performance corresponding to the time when the traffic data of the first application is congestion controlled based on the adjusted first congestion control algorithm index.

S804. Input the second transmission performance index into the objective function to obtain a second evaluation value.

S805. Determine whether the second evaluation value is smaller than the first evaluation value. If yes, execute S806, otherwise, execute S807.

S806. Replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return to performing S801.

S807. Replace the initial congestion parameter with the adjusted first congestion parameter, adjust the first congestion parameter according to other adjustment directions in the multiple adjustment directions, and obtain multiple adjusted first congestion parameters; based on the multiple adjusted first congestion parameters For the first congestion parameter, return to execute S802-S804 respectively, obtain a plurality of second evaluation values, and then execute S808.

S808. Determine whether there is at least one second evaluation value in the plurality of second evaluation values that is smaller than the first evaluation value. If it exists, execute S809, otherwise, execute S810.

S809: Replace the first adjustment direction with an adjustment direction corresponding to the smallest second evaluation value among the at least one second evaluation value, replace the first evaluation value with the smallest second evaluation value, and return to executing S801.

S810. Determine the first evaluation value as the minimum evaluation value of the objective function, and use the first congestion parameter currently corresponding to the first evaluation value as the first congestion parameter finally corresponding to the first application type of the first application.

The steps S801 to S810 are similar to the steps S502 to S511 shown in FIG. 8 above, and the specific process can refer to the relevant descriptions of the above steps S502 to S511 , which will not be repeated here.

In some embodiments, after the network device adjusts the first congestion parameter corresponding to the first application type of the first application, the network device may update the mapping relationship between the application type and the congestion parameter based on the adjusted first congestion parameter, to The network device can subsequently perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm obtained based on the adjusted first congestion parameter, so that the network device can effectively control the first application in different network environments. When an application performs congestion control, further, limited network bandwidth resources can be allocated without affecting the user's experience of using the first application, which can improve the utilization rate of network bandwidth resources.

In the embodiment of the present application, since the first congestion parameter of the first congestion control algorithm used by the network device to perform congestion control on the traffic data of different applications is determined based on the respective first application types of different applications, it can effectively Congestion control is performed on the traffic data of the first application, and further, limited network bandwidth resources can be allocated without affecting the user's experience of using different applications, which can improve the utilization rate of network bandwidth resources. In addition, the network device can also adjust the first congestion parameters corresponding to the first application types of different applications, so that they can be applied to different network environments.

In another embodiment, taking the network system shown in FIGS. 1-3 applied to the network system shown in FIG. 4 as an example, as shown in FIG. 12 , a flowchart of a congestion control method provided by this embodiment of the present application is shown. Schematic. Among them, Fig. 12 takes the execution subject as the adjustment device as an example. As shown in Figure 12, the method flow includes the following steps:

S901. Acquire a first transmission performance indicator corresponding to when congestion control is performed on traffic data of a first application based on a first congestion control algorithm.

In some embodiments, the adjustment device may monitor the first transmission performance index corresponding to when the network device performs congestion control on the traffic data of the first application based on the first congestion control algorithm, that is, the adjustment device may actively obtain the first congestion control algorithm based on the first transmission performance index. The first transmission performance index corresponding to the congestion control of the traffic data of the first application. Alternatively, the adjustment device may acquire the first transmission performance indicator that is sent by the network device and corresponds to when it performs congestion control on the traffic data of the first application based on the first congestion control algorithm. For example, the network device may record the corresponding first transmission performance index when it performs congestion control on the traffic data of the first application based on the first congestion control algorithm. Afterwards, the network device may send the recorded first transmission performance index corresponding to when the traffic data of the first application is subjected to congestion control based on the first congestion control algorithm to the adjustment device.

S902. Adjust a first congestion parameter corresponding to a first application type of the first application according to the first transmission performance indicator. The adjusted first congestion parameter is used to obtain an adjusted first congestion control algorithm, and the adjusted first congestion control algorithm is used to perform congestion control on the traffic data of the first application.

In some embodiments, the adjustment device may acquire the first congestion parameter corresponding to the first application type of the first application. For example, the adjustment device may acquire the mapping relationship between the application type and the congestion parameter, and may acquire the first congestion parameter corresponding to the first application type of the first application based on the mapping relationship and the first application type of the first application. Optionally, the mapping relationship may include multiple application types and respective congestion parameters corresponding to the multiple application types. In a specific implementation process, the multiple application types included in the mapping relationship may include multiple second application types, and may also include at least one first application type included in at least one second application type among the multiple second application types. An application type, that is, the first application type belongs to the second application type. Specifically, the multiple second application types may include, but are not limited to: game application types, online video application types, short video application types, online music application types, VR application types, and web page application types, etc. This is not specifically limited in the application examples. As an example, taking a second application type among the plurality of second application types as an example of a game application type, the second application type may include the first application type such as the King of Glory application type or the Peace Hero application type.

In some embodiments, the adjustment device may acquire the first congestion parameter corresponding to the first application type of the first application based on the first application type of the first application and the mapping relationship. Wherein, the mapping relationship may be one or any combination of the adjustment device stored in the local storage, the external storage connected to the adjustment device, other devices (such as network devices) connected to the adjustment device, the cloud, and the like. There is no specific limitation.

As an example, for any application type in at least one application type in the mapping relationship between the application type and the congestion parameter, for simplicity, the application type is called application type b as an example, the congestion corresponding to the application type b The parameter may be obtained by training the adjustment device based on the traffic data of at least one application corresponding to the application type b by means of reinforcement learning. The application type b generally refers to the second application type.

The process of obtaining the congestion parameter corresponding to application type b by the adjustment device is similar to the process of obtaining the congestion parameter corresponding to application type a by the network device shown in FIG. 7 or FIG. 8 . For details, refer to steps S401-S411 shown in FIG. Or the related descriptions of steps S501-S511 shown in FIG. 8 will not be repeated here.

Wherein, since the application type b can correspond to at least one application, when the at least one application corresponding to the application type b includes multiple applications, the adjustment device can select an application among the multiple applications, and the adjustment device can select one of the multiple applications. The shown network device obtains the congestion parameter corresponding to the application type a. Alternatively, since different applications may have small differences in transmission performance indicators, the adjustment device may, based on multiple applications, adopt the method of obtaining multiple congestion parameters corresponding to the application type a as shown in the above-mentioned FIG. 7 or FIG. 8 by the network device , to obtain multiple congestion parameters corresponding to the application type a. Afterwards, the adjustment device can obtain the final congestion parameter corresponding to application type b in a corresponding manner. For example, the average value of multiple congestion parameters corresponding to application type b can be taken as the final congestion parameter corresponding to application type b.

It should be noted that the congestion parameter corresponding to the application type b in the above mapping relationship can be obtained by adjusting the device offline through the test network to obtain the application type a by training the network device as shown in Figure 7 or Figure 8. .

It should be noted that the above is an example of the first application type including the first application in the mapping relationship between the application type and the congestion parameter. In a specific implementation process, when the mapping relationship between the application type and the congestion parameter does not include the first application type of the first application, the adjustment device may determine the first application type according to the second application type of the first application and the mapping relationship A first congestion parameter corresponding to an application type. Afterwards, the adjustment device may update the mapping relationship according to the first congestion parameter corresponding to the first application type of the first application. For example, taking the first application as the King of Glory as an example, when the mapping relationship only includes the game application type, that is, does not include the King of Glory application type, the adjustment device can determine the King of Glory application according to the game application type and the mapping relationship. The first congestion parameter corresponding to the type.

The following specifically describes a process for the adjustment device to acquire the first congestion parameter corresponding to the first application type according to the second application type and the mapping relationship of the first application.

In some embodiments, after acquiring the first application type of the first application, the adjustment device may determine the second application type of the first application according to the first application type of the first application. Afterwards, the adjustment device may acquire the second congestion parameter corresponding to the second application type of the first application according to the second application type of the first application and the mapping relationship. At this time, adjusting the second congestion parameter corresponding to the second application type of the first application obtained by the device can be understood as initializing the value of the first congestion parameter corresponding to the first application type of the first application, that is, the mapping The value of the second congestion parameter corresponding to the second application type of the first application included in the relationship is the initial value of the first congestion parameter corresponding to the first application type of the first application. After that, the adjustment device may use reinforcement learning to perform training based on the second congestion parameter corresponding to the second application type of the first application and the traffic data of the first application to obtain the first congestion corresponding to the first application type of the first application. parameter. For example, the adjustment device may obtain the second congestion control algorithm based on the second congestion parameter corresponding to the second application type of the first application, and may obtain the second congestion control algorithm corresponding to the congestion control of the traffic data of the first application based on the second congestion control algorithm. The third transmission performance index is input into the objective function to obtain the third evaluation value. Afterwards, the adjustment device may perform training based on the third evaluation value and the traffic data of the first application in a reinforcement learning manner to obtain the first congestion parameter corresponding to the first application type. The process for the adjustment device to obtain the first congestion parameter corresponding to the first application type is similar, and the process for the network device to obtain the first congestion parameter corresponding to the first application type is similar. For the specific training process, refer to steps S401-S411 shown in FIG. The related descriptions of steps S501-S511 shown in FIG. 8 will not be repeated here.

It should be noted that, when the mapping relationship between the application type and the congestion parameter does not include the first application type and the second application type of the first application, the adjustment device can obtain the first application in the manner shown in FIG. 7 or FIG. 8 The first congestion parameter corresponding to the first application type and/or the second congestion parameter corresponding to the second application type, the specific process can refer to steps S401-S411 shown in FIG. 7 or steps S501-S511 shown in FIG. 8 . Relevant descriptions are not repeated here.

It should be noted that when the mapping relationship between the application type and the congestion parameter does not include the first congestion parameter corresponding to the first application type of the first application, the first congestion parameter corresponding to the first application type of the first application may be It is obtained by training the adjustment device online in the manner shown in FIG. 7 or FIG. 8 , that is, the adjustment device is trained in the manner shown in FIG. 7 or FIG. 8 when the first application is used.

In the embodiment of the present application, due to the first congestion parameter corresponding to the first application type of the first application, the adjustment device adopts the reinforcement learning method to perform training based on the requirements of the first application for transmission performance indicators and the traffic data of the first application obtained, it can be guaranteed that the first congestion control algorithm obtained based on the first congestion parameter is suitable for performing congestion control on the traffic data of the first application, and can effectively perform congestion control on the traffic data of the first application, and further, The limited network bandwidth resources can be allocated on the basis of not affecting the user's experience of using the first application, which can improve the utilization rate of the network bandwidth resources.

In some embodiments, before acquiring the first congestion parameter corresponding to the first application type of the first application, the adjustment device may further acquire the first application type of the first application. For example, the network device sends the first application type of the first application identified by the identification device to the adjustment device. Correspondingly, the adjustment device may acquire the first application type of the first application. Alternatively, when the identification device is integrated on the network device, the adjustment device may acquire the first application type of the first application identified by the network device. Or, when the identification device is integrated on the adjustment device, the adjustment device can identify the first application type of the first application. For the specific process of identifying the first application type of the first application, reference may be made to the process of identifying the first application type of the first application shown in the above S201, which will not be repeated here.

In some embodiments, after acquiring the first transmission performance indicator, the adjustment device may adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator.

In some embodiments, the adjustment device may acquire the requirements of the first application for the transmission performance index according to the first transmission performance index. The specific implementation process for the adjustment device to acquire the requirements of the first application for transmission performance indicators is similar to the specific implementation process for the network device to acquire the requirements of the first application for transmission performance indicators. The relevant descriptions of the requirements of the transmission performance indicators will not be repeated here. After that, the adjustment device may adjust the first congestion parameter corresponding to the first application type of the first application based on the first application's requirement for the transmission performance indicator. For example, the adjustment device can evaluate the requirements of the first application on the transmission performance index by acquiring the objective function. In other words, the objective function can be used to measure the effect of the first congestion control algorithm on the congestion control of the traffic data of the first application, that is, to measure whether the first congestion control algorithm can meet the requirements of the first application for transmission performance indicators. Afterwards, the adjustment device may input the first transmission performance index into the objective function to obtain the first evaluation value. The adjusting device may adjust the first congestion parameter based on the first evaluation value.

The process of adjusting the first congestion parameter by the adjusting device based on the first evaluation value is similar to the process of adjusting the first congestion parameter by the network device based on the first evaluation value. For details, refer to steps S701-S710 shown in FIG. 10 or FIG. 11 . The related descriptions of the illustrated steps S801-S810 will not be repeated here.

In this embodiment of the present application, since the network environment may change, during the process of running the first application on the terminal, the adjustment device may adjust the first congestion parameter corresponding to the first application type of the first application, so that the network device can operate in different It can effectively control the congestion of the traffic data of the first application in the network environment of the first application. Furthermore, on the basis of not affecting the user's experience of using the first application, limited network bandwidth resources can be allocated, which can improve the utilization of network bandwidth resources. Rate.

In some embodiments, after the adjustment device adjusts the first congestion parameter corresponding to the first application type of the first application, the adjustment device may update the mapping relationship between the application type and the congestion parameter based on the adjusted first congestion parameter. The adjustment device may also send the adjusted first congestion parameter to the network device, so that the network device can subsequently perform the first application traffic data based on the adjusted first congestion control algorithm obtained based on the adjusted first congestion parameter. Congestion control, so that the network device can effectively perform congestion control on the traffic data of the first application in different network environments, and further, can allocate a limited network on the basis of not affecting the user's experience of using the first application Bandwidth resources can improve the utilization of network bandwidth resources.

It should be understood that, in the embodiments of the present application, the network device or the adjustment device may perform some or all of the steps in the embodiments of the present application, these steps are only examples, and the embodiments of the present application may also perform other steps or variations of various steps. In addition, various steps may be performed in different orders presented in the embodiments of the present application, and it may not be necessary to perform all the steps in the embodiments of the present application.

In the various embodiments of the present application, if there is no special description or logical conflict, the terms and/or descriptions between different embodiments are consistent and can be referred to each other, and the technical features in different embodiments are based on their inherent Logical relationships can be combined to form new embodiments.

It should be understood that, in order to implement the above-mentioned functions, the network device or the adjustment device includes corresponding hardware structures and/or software modules for executing each function. Those skilled in the art should easily realize that the present application can be implemented in hardware or a combination of hardware and computer software with the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

In this embodiment of the present application, the network device or the adjustment device can be divided into functional modules according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. It should be noted that, the division of modules in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

In the case of using an integrated unit (module), FIG. 13 shows a schematic structural diagram of a network device provided by an embodiment of the present application. As shown in FIG. 13 , the network device 1000 may include: an obtaining unit 1001 and a processing unit 1002 .

The obtaining unit 1001 is configured to support the network device 1000 to obtain the first application type of the first application. Specifically, when the network device 1000 obtains the first application type of the first application from other devices, the obtaining unit 1001 may support communication between the network device and other devices, such as communication with the identification device. The processing unit 1002 is used to control and manage the actions of the network device 1000, for example, the processing unit 1002 is used to support the network device 1000 to perform the processes shown in FIGS. other processes. Specifically, you can refer to the following description:

an obtaining unit 1001, configured to obtain a first application type of a first application;

A processing unit 1002, configured to obtain, according to the first application type, a first congestion parameter corresponding to the first application type, where the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control algorithm for performing congestion control on the traffic data of the first application.

In a possible design, after the processing unit 1002 is configured to obtain, according to the first application type, the first congestion parameter corresponding to the first application type, the processing unit 1002 may also be configured to: obtain the first congestion parameter based on the first congestion parameter. the first congestion control algorithm; and based on the first congestion control algorithm, congestion control is performed on the traffic data of the first application.

In a possible design, after the processing unit 1002 is configured to perform congestion control on the traffic data of the first application based on the first congestion control algorithm, the processing unit 1002 may also be configured to: obtain a pair of data based on the first congestion control algorithm. The first transmission performance index corresponding to the traffic data of the first application when congestion control is performed; the first congestion parameter is adjusted according to the first transmission performance index.

In a possible design, when the processing unit 1002 is configured to adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, the processing unit 1002 may be specifically configured to: according to the first The transmission performance indicator is to obtain the requirements of the first application for the transmission performance indicator; and the first congestion parameter is adjusted according to the requirements of the first application for the transmission performance indicator.

In a possible design, the processing unit 1002 is configured to adjust the first congestion parameter according to the requirements of the first application on the transmission performance indicator, which may be specifically used to: input the first transmission performance indicator into a target function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index; and based on the first evaluation value, the first congestion parameter is adjusted.

In a possible design, the first transmission performance indicator may include at least two performance indicators, such as throughput and delay; the first application may perform at least one of the at least two performance indicators. When the indicator is high demand, the processing unit 1002 may adjust the first congestion parameter in the following manner:

In a possible design, the transmission performance indicator may include at least two performance indicators, such as throughput and delay; when the first application has low requirements for the at least two performance indicators, processing Unit 1002 may adjust the first congestion parameter in the following manner:

The window reduction algorithm is characterized as:

cwnd=cwnd(1-β)

In a possible design, when the processing unit 1002 is configured to acquire the first congestion parameter corresponding to the first application type according to the first application type, the processing unit 1002 may be configured to: acquire the mapping between the application type and the congestion parameter relationship; based on the mapping relationship and the first application type, obtain a first congestion parameter corresponding to the first application type. The mapping relationship may be, but not limited to, stored in the local storage of the network device 1000, an external storage connected to the network device 1000, and the cloud.

In a possible design, the mapping relationship may include multiple application types and congestion parameters corresponding to the multiple application types; for any application type in the at least one application type in the mapping relationship, the processing unit 1002 may determine the congestion parameter corresponding to the application type in the following manner: obtain the initial congestion parameter corresponding to the application type, and obtain the initial congestion control algorithm corresponding to the application type based on the initial congestion parameter corresponding to the application type; The initial congestion control algorithm corresponding to the application type performs congestion control on the traffic data of at least one application corresponding to the application type, and obtains the initial transmission performance index corresponding to the at least one application; The initial transmission performance index is input into the objective function, and at least one initial evaluation value is obtained, and the objective function is used to evaluate the respective requirements of the at least one application on the transmission performance index; the reinforcement learning method is adopted based on the at least one initial evaluation value and all The traffic data of the at least one application is trained to obtain a congestion parameter corresponding to the application type.

In a possible design, when the processing unit 1002 is configured to obtain the first congestion parameter corresponding to the first application type based on the mapping relationship and the first application type, it may be specifically configured to: if the mapping If the relationship does not include the first application type, then obtain the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship; or, if the If the mapping relationship includes the first application type, the first congestion parameter corresponding to the first application type is acquired according to the first application type and the mapping relationship.

In a possible design, when the processing unit 1002 is configured to obtain the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship, the processing unit 1002 may specifically use In: obtaining a second congestion parameter corresponding to the second application type to which the first application type belongs, according to the second application type to which the first application type belongs and the mapping relationship, and obtaining the second congestion parameter based on the second congestion parameter Two congestion control algorithms; a third transmission performance index corresponding to when congestion control is performed on the traffic data of the first application based on the second congestion control algorithm; inputting the third performance index into an objective function to obtain a third evaluation value ; The objective function is used to evaluate the requirements of the first application to the transmission performance index; The reinforcement learning method is used to train based on the third evaluation value and the traffic data of the first application to obtain the first application type The corresponding first congestion parameter.

In a possible design, after the processing unit 1002 is configured to adjust the first congestion parameter according to the first transmission performance indicator, the processing unit 1002 may also be configured to: update the mapping relationship based on the adjusted first congestion parameter .

It should be understood that the operations and/or functions of each module in the network device 1000 are respectively to implement the corresponding processes of the congestion control methods shown in FIGS.

In the case of using an integrated unit (module), FIG. 14 shows a schematic structural diagram of a network device provided by an embodiment of the present application. As shown in FIG. 14 , the adjustment device 1100 may include: an acquisition unit 1101 and a processing unit 1102 .

The obtaining unit 1101 is configured to support the adjustment device 1100 to obtain the first application type of the first application. Specifically, when the adjustment device 1100 obtains the first application type of the first application from other devices, the obtaining unit 1101 may support communication between the adjustment device and other devices, such as communication with the identification device and/or the network device. The processing unit 1102 is used to control and manage the actions of the adjustment device 1100. For example, the processing unit 1102 is used to support the adjustment device 1100 to perform the process shown in FIG. 12, and/or other processes for the techniques described herein. Specifically, you can refer to the following description:

An obtaining unit 1101, configured to obtain a first transmission performance indicator corresponding to when congestion control is performed on the traffic data of the first application based on the first congestion control algorithm;

A processing unit 1102, configured to adjust a first congestion parameter corresponding to a first application type of the first application according to the first transmission performance index, and the adjusted first congestion parameter is used to obtain an adjusted first congestion control algorithm , and the adjusted first congestion control algorithm is used to perform congestion control on the traffic data of the first application.

In a possible design, when the processing unit 1102 is configured to adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, it may be specifically configured to: according to the first The transmission performance indicator is to obtain the requirements of the first application for the transmission performance indicator; and the first congestion parameter is adjusted according to the requirements of the first application for the transmission performance indicator.

In a possible design, when the processing unit 1102 is configured to adjust the first congestion parameter according to the requirements of the first application on the transmission performance indicator, it may be specifically configured to: input the first transmission performance indicator into a target function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index; and based on the first evaluation value, the first congestion parameter is adjusted.

The window reduction algorithm is characterized as:

cwnd=cwnd(1-β)

In a possible design, the first transmission performance indicator may include at least two performance indicators, such as throughput and delay; the first application may perform at least one of the at least two performance indicators. When the indicator is high demand, the processing unit 1102 may adjust the first congestion parameter in the following manner:

In a possible design, the transmission performance indicator may include at least two performance indicators, such as throughput and delay; when the first application has low requirements for the at least two performance indicators, processing The unit 1102 may adjust the first congestion parameter in the following manner, including:

In a possible design, before the processing unit 1102 is configured to adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, the processing unit 1102 may also be configured to: obtain the application type and the congestion parameter A mapping relationship between parameters; based on the mapping relationship and the first application type, obtain a first congestion parameter corresponding to the first application type. The mapping relationship may be, but not limited to, stored in the local memory of the adjustment device 1100, an external memory connected to the adjustment device 1100, other devices (eg, network devices) connected to the adjustment device 1100, and the cloud.

In a possible design, the mapping relationship may include multiple application types and congestion parameters corresponding to the multiple application types; for any application type in the at least one application type in the mapping relationship, the processing unit 1102 may determine the congestion parameter corresponding to the application type in the following manner: obtain the initial congestion parameter corresponding to the application type, and obtain the initial congestion control algorithm corresponding to the application type based on the initial congestion parameter corresponding to the application type; The initial congestion control algorithm corresponding to the application type performs congestion control on the traffic data of at least one application corresponding to the application type, and obtains the initial transmission performance index corresponding to the at least one application; The initial transmission performance index is input into the objective function, and at least one initial evaluation value is obtained, and the objective function is used to evaluate the respective requirements of the at least one application on the transmission performance index; the reinforcement learning method is adopted based on the at least one initial evaluation value and all The traffic data of the at least one application is trained to obtain a congestion parameter corresponding to the application type.

In a possible design, when the processing unit 1102 is configured to acquire the first congestion parameter corresponding to the first application type based on the mapping relationship and the first application type, the processing unit 1102 may be specifically configured to: if the mapping If the relationship does not include the first application type, then obtain the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship; or, if the If the mapping relationship includes the first application type, the first congestion parameter corresponding to the first application type is acquired according to the first application type and the mapping relationship.

In a possible design, when the processing unit 1102 is configured to acquire the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship, the processing unit 1102 may specifically use In: obtaining a second congestion parameter corresponding to the second application type to which the first application type belongs, according to the second application type to which the first application type belongs and the mapping relationship, and obtaining the second congestion parameter based on the second congestion parameter Two congestion control algorithms; a third transmission performance index corresponding to when congestion control is performed on the traffic data of the first application based on the second congestion control algorithm; inputting the third performance index into an objective function to obtain a third evaluation value ; The objective function is used to evaluate the requirements of the first application to the transmission performance index; The reinforcement learning method is used to train based on the third evaluation value and the traffic data of the first application to obtain the first application type The corresponding first congestion parameter.

It should be understood that the operations and/or functions of the various modules in the adjustment device 1100 are respectively to implement the corresponding flow of the congestion control method shown in FIG. 12 , and are not repeated here for brevity.

In the case of using an integrated unit (module), in the case of using an integrated unit (module), FIG. 15 shows a schematic structural diagram of a network device provided by an embodiment of the present application. As shown in FIG. 15 , the network device 1200 may include at least one processor 1201 and a memory 1202 ; the memory 1202 stores one or more computer programs, such as for storing one or more computer programs necessary for the network device 1200 . The at least one processor 1201 is configured to support the network device 1200 to implement the above congestion control method. For example, when one or more computer programs stored in the memory 1202 are executed by the at least one processor 1201, the network device 1200 may implement any of the possibilities shown in Figures 5-11, and/or be used to implement other embodiments described herein.

In the case of using an integrated unit (module), in the case of using an integrated unit (module), FIG. 16 shows a schematic structural diagram of an adjustment device provided by an embodiment of the present application. As shown in FIG. 16 , the adjustment device 1300 may include at least one processor 1301 and a memory 1302 ; the memory 1302 stores one or more computer programs, for example, for storing one or more computer programs necessary for the adjustment device 1300 . The at least one processor 1301 is configured to support the adjustment device 1300 to implement the above-mentioned congestion control method. For example, when one or more computer programs stored in the memory 1302 are executed by the at least one processor 1301, the adjustment device 1300 may implement any of the possibilities shown in FIG. 12, and/or be used to implement other embodiments described herein.

Based on the same concept as the foregoing method embodiments, the embodiments of the present application further provide a computer-readable storage medium or a non-volatile storage medium, where the computer-readable storage medium or the non-volatile storage medium stores computer instructions or A computer program, when the computer instructions or computer programs are run on a computer, causing the computer to execute the above-mentioned embodiments of the congestion control method, any possible implementation of the embodiments, or when the computer instructions or computer programs are executed. When running on one or more processors, the network device or adjustment device including the one or more processors is made to execute the embodiments of the congestion control method and any possible implementation manners of the embodiments, such as the execution diagram of the 5—Any steps of the embodiments of the congestion control method shown in FIG. 11 or FIG. 12, and/or other processes that perform the techniques described herein.

Based on the same concept as the above method embodiments, the embodiments of the present application also provide a program product, the computer program product is used to store a computer program, and when the computer program runs on a computer, the computer is made to execute the above congestion Embodiments of the control method, any possible implementations of the embodiments, or when the computer instructions or computer programs run on one or more processors, make a network device including the one or more processors Or adjust the device to perform the above-mentioned embodiment of the congestion control method and any possible implementation manner of the embodiment, for example, perform any step of the embodiment of the congestion control method shown in FIG. 5-FIG. 11 or FIG. 12 , and/or perform Other procedures for the techniques described herein.

It should be understood that the processor in the embodiment of the present application (the processor shown in FIG. 15 and FIG. 16 ) may be an integrated circuit chip, which has the capability of processing signals. In the implementation process, each step of the above-mentioned embodiment of the congestion control method may be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The above-mentioned processor can be a general-purpose central processing unit (central processing unit, CPU), a general-purpose processor, a digital signal processing (digital signal processing, DSP), an application specific integrated circuit (application specific integrated circuits, ASIC), a field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof; it may also be a combination that implements computing functions, such as a combination of one or more microprocessors, DSP and microprocessor combination of devices, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It should be understood that the memory (the memory shown in FIG. 15 and FIG. 16 ) in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory . The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory may be random access memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM) ) and direct memory bus random access memory (direct rambus RAM, DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but not be limited to, these and any other suitable types of memory.

The various illustrative logic units and circuits described in the embodiments of the present application can be implemented by general-purpose processors, digital signal processors, application-specific integrated circuits (ASICs), field programmable gate arrays (field programmable gate arrays). , FPGA) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination of the above designed to implement or operate the described functions. A general-purpose processor may be a microprocessor, or alternatively, the general-purpose processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors in combination with a digital signal processor core, or any other similar configuration. accomplish.

The steps of the method or algorithm described in the embodiments of this application may be directly embedded in hardware, a software unit executed by a processor, or a combination of the two. The software unit may be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. Illustratively, a storage medium may be coupled to the processor such that the processor may read information from, and store information in, the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium may be provided in an ASIC, which may be provided in the network device or the adjustment device, for example, in different components of the network device or the adjustment device.

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented in software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are executed in whole or in part. The computer may be a general purpose computer, special purpose computer, computer network, or other programmable device. The computer program or instructions may be stored in or transmitted over a computer-readable storage medium. The computer-readable storage medium can be any available media that can be accessed by a computer or a data storage device such as a server that integrates one or more available media. The usable media may be magnetic media, such as floppy disks, hard disks, magnetic tapes; optical media, such as DVDs; and semiconductor media, such as solid state disks (SSD).

The embodiments of the present application are described with reference to the flowcharts and/or block diagrams of the methods, apparatuses, and computer program products involved in the embodiments. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

Although the embodiments of the present application have been described in conjunction with specific features, it will be apparent that various modifications and combinations may be made without departing from the spirit and scope of the embodiments of the present application. Accordingly, the present specification and drawings are merely illustrative of the embodiments of the present application as defined by the appended claims, and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the embodiments of the present application.

Claims

A congestion control method, comprising:

Obtain the first application type of the first application;

According to the first application type, a first congestion parameter corresponding to the first application type is obtained, the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control algorithm is used to The traffic data of an application performs congestion control.
The method according to claim 1, wherein after acquiring the first congestion parameter corresponding to the first application type according to the first application type, the method further comprises:

obtaining the first congestion control algorithm based on the first congestion parameter;

Congestion control is performed on the traffic data of the first application based on the first congestion control algorithm.
The method according to claim 2, wherein after performing congestion control on the traffic data of the first application based on the first congestion control algorithm, the method further comprises:

acquiring a first transmission performance indicator corresponding to when congestion control is performed on the traffic data of the first application based on the first congestion control algorithm;

The first congestion parameter is adjusted according to the first transmission performance index.
The method of claim 3, wherein adjusting the first congestion parameter according to the first transmission performance indicator comprises:

Obtaining, according to the first transmission performance indicator, a requirement of the first application for the transmission performance indicator;

The first congestion parameter is adjusted according to the requirements of the first application for transmission performance indicators.
The method according to claim 4, wherein adjusting the first congestion parameter according to the requirements of the first application on the transmission performance indicator comprises:

Inputting the first transmission performance index into an objective function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index;

Based on the first evaluation value, the first congestion parameter is adjusted.
The method according to claim 5, wherein the first transmission performance indicator comprises at least two performance indicators; when the first application has high requirements on at least one of the at least two performance indicators , adjust the first congestion parameter in the following manner:

Adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions to obtain the adjusted first congestion parameter;

obtaining an adjusted first congestion control algorithm based on the adjusted first congestion parameter;

Congestion control is performed on the traffic data of the first application based on the adjusted first congestion control algorithm, and the corresponding second Transmission performance indicators;

Inputting the second transmission performance index into the objective function to obtain a second evaluation value;

If the second evaluation value is greater than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return Adjusting the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions is performed to obtain the adjusted first congestion parameter; or,

If the second evaluation value is smaller than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, and adjust the first congestion parameter according to other adjustment directions among the plurality of adjustment directions. a congestion parameter to obtain a plurality of adjusted first congestion parameters, and the other adjustment directions are adjustment directions other than the first adjustment direction among the plurality of adjustment directions; based on the plurality of adjusted first congestion parameters parameters, respectively return to execute the adjusted first congestion control algorithm based on the adjusted first congestion parameters, until multiple second evaluation values are obtained; when at least one of the multiple second evaluation values is greater than When the first evaluation value is used, the first adjustment direction is replaced with the adjustment direction corresponding to the largest second evaluation value in the at least one second evaluation value, and the first evaluation value is replaced by the largest second evaluation value. For the second evaluation value, return to adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions, and obtain the adjusted first congestion parameter; when the plurality of second evaluation values are all smaller than the first adjustment direction When the evaluation value is obtained, the first evaluation value is determined as the maximum evaluation value of the objective function, and the first congestion parameter currently corresponding to the first evaluation value is used as the final first congestion parameter.
The method according to claim 5, wherein the transmission performance indicators include at least two performance indicators; when the first application has low requirements for the at least two performance indicators, the following methods are used to adjust the The first congestion parameters include:

Adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions to obtain the adjusted first congestion parameter;

obtaining an adjusted first congestion control algorithm based on the adjusted first congestion parameter;

Congestion control is performed on the traffic data of the first application based on the adjusted first congestion control algorithm, and the corresponding second Transmission performance indicators;

Inputting the second transmission performance index into the objective function to obtain a second evaluation value;

If the second evaluation value is smaller than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return Adjusting the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions is performed to obtain the adjusted first congestion parameter; or,

If the second evaluation value is greater than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, and adjust the first congestion parameter according to other adjustment directions among the plurality of adjustment directions. a congestion parameter to obtain a plurality of adjusted first congestion parameters, and the other adjustment directions are adjustment directions other than the first adjustment direction among the plurality of adjustment directions; based on the plurality of adjusted first congestion parameters parameters, respectively return to execute the adjusted first congestion control algorithm based on the adjusted first congestion parameters, until multiple second evaluation values are obtained; when at least one of the multiple second evaluation values is less than In the case of the first evaluation value, the first adjustment direction is replaced with the adjustment direction corresponding to the smallest second evaluation value among the at least one second evaluation value, and the first evaluation value is replaced by the smallest second evaluation value. For the second evaluation value, return to adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions, and obtain the adjusted first congestion parameter; when the plurality of second evaluation values are all greater than the first adjustment direction When the evaluation value is obtained, the first evaluation value is determined as the minimum evaluation value of the objective function, and the first congestion parameter currently corresponding to the first evaluation value is used as the final first congestion parameter.
The method according to claim 6 or 7, wherein the first congestion parameter includes at least a first sub-parameter and a second sub-parameter;

The multiple adjustment directions include the following four adjustment directions, and the first adjustment direction is any one of the following four adjustment directions:

increasing the first sub-parameter and the second sub-parameter;

increasing the first sub-parameter and decreasing the second sub-parameter;

Decrease the first sub-parameter and increase the second sub-parameter;

Decrease the first subparameter and the second subparameter.
The method according to claim 8, wherein the first congestion control algorithm includes a window raising algorithm and a window lowering algorithm, the first sub-parameter is a parameter corresponding to the window raising algorithm, and the second sub-parameter is a parameter corresponding to the window raising algorithm. The parameters are parameters corresponding to the window reduction algorithm.
The method of claim 9, wherein the window raising algorithm is characterized as:

The window reduction algorithm is characterized as:

cwnd=cwnd(1-β)

Wherein, cwnd is used to represent the congestion window value, α is the first sub-parameter, and β is the second sub-parameter.
The method according to any one of claims 1-10, wherein obtaining the first congestion parameter corresponding to the first application type according to the first application type, comprising:

Obtain the mapping relationship between application types and congestion parameters;

Based on the mapping relationship and the first application type, a first congestion parameter corresponding to the first application type is acquired.
The method according to claim 11, wherein the mapping relationship includes multiple application types and congestion parameters corresponding to the multiple application types; for any application in at least one application type in the mapping relationship Type, determine the congestion parameter corresponding to the application type in the following way:

obtaining an initial congestion parameter corresponding to the application type, and obtaining an initial congestion control algorithm corresponding to the application type based on the initial congestion parameter corresponding to the application type;

Based on the initial congestion control algorithm corresponding to the application type, congestion control is performed on the traffic data of at least one application corresponding to the application type, and the initial transmission performance index corresponding to the at least one application is obtained;

Inputting the respective initial transmission performance indicators of the at least one application into an objective function to obtain at least one initial evaluation value, and the objective function is used to evaluate the respective requirements of the at least one application on the transmission performance indicators;

The training is performed based on the at least one initial evaluation value and the respective traffic data of the at least one application in a reinforcement learning manner, and the congestion parameter corresponding to the application type is obtained.
The method according to claim 11 or 12, wherein obtaining the first congestion parameter corresponding to the first application type based on the mapping relationship and the first application type, comprising:

If the mapping relationship does not include the first application type, obtain a first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship; or ,

If the mapping relationship includes the first application type, obtain a first congestion parameter corresponding to the first application type according to the first application type and the mapping relationship.
The method according to claim 13, wherein obtaining the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship, comprising:

According to the second application type to which the first application type belongs and the mapping relationship, a second congestion parameter corresponding to the second application type to which the first application type belongs is obtained, and a second congestion parameter is obtained based on the second congestion parameter control algorithm;

acquiring a third transmission performance indicator corresponding to when congestion control is performed on the traffic data of the first application based on the second congestion control algorithm;

Inputting the third performance index into an objective function to obtain a third evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index;

The reinforcement learning method is used to perform training based on the third evaluation value and the traffic data of the first application, so as to obtain the first congestion parameter corresponding to the first application type.
The method according to claim 11, wherein after adjusting the first congestion parameter according to the first transmission performance indicator, the method further comprises:

Based on the adjusted first congestion parameter, the mapping relationship is updated.
The method according to any one of claims 3-15, wherein the first transmission performance indicator includes throughput and delay.
A congestion control method, comprising:

acquiring a first transmission performance indicator corresponding to when congestion control is performed on the traffic data of the first application based on the first congestion control algorithm;

The first congestion parameter corresponding to the first application type of the first application is adjusted according to the first transmission performance index, and the adjusted first congestion parameter is used to obtain an adjusted first congestion control algorithm. The congestion control algorithm is used to perform congestion control on the traffic data of the first application.
The method according to claim 17, wherein adjusting the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator comprises:

Obtaining, according to the first transmission performance indicator, a requirement of the first application for the transmission performance indicator;

The first congestion parameter is adjusted according to the requirements of the first application for transmission performance indicators.
The method according to claim 18, wherein adjusting the first congestion parameter according to the requirements of the first application on the transmission performance index, comprising:

Inputting the first transmission performance index into an objective function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index;

Based on the first evaluation value, the first congestion parameter is adjusted.
The method according to any one of claims 17-19, wherein the first transmission performance indicator comprises at least two performance indicators; and the first application performs at least one of the at least two performance indicators When the indicator is of high demand, the first congestion parameter is adjusted in the following manner:

Adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions to obtain the adjusted first congestion parameter;

obtaining an adjusted first congestion control algorithm based on the adjusted first congestion parameter;

Congestion control is performed on the traffic data of the first application based on the adjusted first congestion control algorithm, and the corresponding second Transmission performance indicators;

Inputting the second transmission performance index into the objective function to obtain a second evaluation value;

If the second evaluation value is greater than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return Adjusting the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions is performed to obtain the adjusted first congestion parameter; or,

If the second evaluation value is smaller than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, and adjust the first congestion parameter according to other adjustment directions among the plurality of adjustment directions. a congestion parameter to obtain a plurality of adjusted first congestion parameters, and the other adjustment directions are adjustment directions other than the first adjustment direction among the plurality of adjustment directions; based on the plurality of adjusted first congestion parameters parameters, respectively return to execute the adjusted first congestion control algorithm based on the adjusted first congestion parameters, until multiple second evaluation values are obtained; when at least one of the multiple second evaluation values is greater than When the first evaluation value is used, the first adjustment direction is replaced with the adjustment direction corresponding to the largest second evaluation value in the at least one second evaluation value, and the first evaluation value is replaced by the largest second evaluation value. For the second evaluation value, return to adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions, and obtain the adjusted first congestion parameter; when the plurality of second evaluation values are all smaller than the first adjustment direction When the evaluation value is obtained, the first evaluation value is determined as the maximum evaluation value of the objective function, and the first congestion parameter currently corresponding to the first evaluation value is used as the final first congestion parameter.
The method according to any one of claims 17 to 19, wherein the transmission performance indicators include at least two performance indicators; when the first application has low requirements for the at least two performance indicators, adopting Adjusting the first congestion parameter in the following manner includes:

Adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions to obtain the adjusted first congestion parameter;

obtaining an adjusted first congestion control algorithm based on the adjusted first congestion parameter;

Congestion control is performed on the traffic data of the first application based on the adjusted first congestion control algorithm, and the corresponding second Transmission performance indicators;

Inputting the second transmission performance index into the objective function to obtain a second evaluation value;

If the second evaluation value is smaller than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, replace the first evaluation value with the second evaluation value, and return Adjusting the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions is performed to obtain the adjusted first congestion parameter; or,

If the second evaluation value is greater than the first evaluation value, replace the first congestion parameter with the adjusted first congestion parameter, and adjust the first congestion parameter according to other adjustment directions among the plurality of adjustment directions. a congestion parameter to obtain a plurality of adjusted first congestion parameters, and the other adjustment directions are adjustment directions other than the first adjustment direction among the plurality of adjustment directions; based on the plurality of adjusted first congestion parameters parameters, respectively return to execute the adjusted first congestion control algorithm based on the adjusted first congestion parameters, until multiple second evaluation values are obtained; when at least one of the multiple second evaluation values is less than In the case of the first evaluation value, the first adjustment direction is replaced with the adjustment direction corresponding to the smallest second evaluation value among the at least one second evaluation value, and the first evaluation value is replaced by the smallest second evaluation value. For the second evaluation value, return to adjust the first congestion parameter according to the first adjustment direction among the plurality of adjustment directions, and obtain the adjusted first congestion parameter; when the plurality of second evaluation values are all greater than the first adjustment direction When the evaluation value is obtained, the first evaluation value is determined as the minimum evaluation value of the objective function, and the first congestion parameter currently corresponding to the first evaluation value is used as the final first congestion parameter.
The method according to claim 20 or 21, wherein the first congestion parameter includes at least a first sub-parameter and a second sub-parameter;

The multiple adjustment directions include the following four adjustment directions, and the first adjustment direction is any one of the following four adjustment directions:

increasing the first sub-parameter and the second sub-parameter;

increasing the first sub-parameter and decreasing the second sub-parameter;

Decrease the first sub-parameter and increase the second sub-parameter;

Decrease the first subparameter and the second subparameter.
The method according to any one of claims 17-22, wherein before adjusting the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, the method further comprises:

Obtain the mapping relationship between application types and congestion parameters;

Based on the mapping relationship and the first application type, a first congestion parameter corresponding to the first application type is acquired.
The method of claim 23, wherein the mapping relationship includes multiple application types and congestion parameters corresponding to the multiple application types; for any application in the at least one application type in the mapping relationship Type, determine the congestion parameter corresponding to the application type in the following way:

obtaining an initial congestion parameter corresponding to the application type, and obtaining an initial congestion control algorithm corresponding to the application type based on the initial congestion parameter corresponding to the application type;

Based on the initial congestion control algorithm corresponding to the application type, congestion control is performed on the traffic data of at least one application corresponding to the application type, and the initial transmission performance index corresponding to the at least one application is obtained;

Inputting the respective initial transmission performance indicators of the at least one application into an objective function to obtain at least one initial evaluation value, and the objective function is used to evaluate the respective requirements of the at least one application on the transmission performance indicators;

The training is performed based on the at least one initial evaluation value and the respective traffic data of the at least one application in a reinforcement learning manner, and the congestion parameter corresponding to the application type is obtained.
The method according to claim 23 or 24, wherein obtaining the first congestion parameter corresponding to the first application type based on the mapping relationship and the first application type, comprising:

If the mapping relationship does not include the first application type, obtain a first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship; or ,

If the mapping relationship includes the first application type, obtain a first congestion parameter corresponding to the first application type according to the first application type and the mapping relationship.
The method of claim 25, wherein obtaining the first congestion parameter corresponding to the first application type according to the second application type to which the first application type belongs and the mapping relationship, comprising:

According to the second application type to which the first application type belongs and the mapping relationship, a second congestion parameter corresponding to the second application type to which the first application type belongs is obtained, and a second congestion parameter is obtained based on the second congestion parameter control algorithm;

a third transmission performance indicator corresponding to when congestion control is performed on the traffic data of the first application based on the second congestion control algorithm;

Inputting the third performance index into an objective function to obtain a third evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index;

The training is performed based on the third evaluation value and the traffic data of the first application in a reinforcement learning manner, and a first congestion parameter corresponding to the first application type is obtained.
The method according to any one of claims 17-26, wherein the first transmission performance indicator includes throughput and delay.
A network device, characterized in that it includes:

an obtaining unit for obtaining the first application type of the first application;

a processing unit, configured to obtain, according to the first application type, a first congestion parameter corresponding to the first application type, where the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control algorithm uses for performing congestion control on the traffic data of the first application.
The device according to claim 28, wherein the processing unit is further configured to: after acquiring the first congestion parameter corresponding to the first application type according to the first application type:

obtaining the first congestion control algorithm based on the first congestion parameter;

Congestion control is performed on the traffic data of the first application based on the first congestion control algorithm.
The device according to claim 29, wherein after the processing unit is configured to perform congestion control on the flow data of the first application based on the first congestion control algorithm, it is further configured to:

acquiring a first transmission performance indicator corresponding to when congestion control is performed on the traffic data of the first application based on the first congestion control algorithm;

The first congestion parameter is adjusted according to the first transmission performance index.
The device according to claim 30, wherein when the processing unit is configured to adjust the first congestion parameter according to the first transmission performance indicator, it is specifically configured to:

Obtaining, according to the first transmission performance indicator, a requirement of the first application for the transmission performance indicator;

The first congestion parameter is adjusted according to the requirements of the first application for transmission performance indicators.
The device according to claim 31, wherein when the processing unit is configured to adjust the first congestion parameter according to the requirements of the first application on the transmission performance indicator, the processing unit is specifically configured to:

Inputting the first transmission performance index into an objective function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index;

Based on the first evaluation value, the first congestion parameter is adjusted.
An adjustment device, characterized in that it includes:

an obtaining unit, configured to obtain the first transmission performance index corresponding to the congestion control of the traffic data of the first application based on the first congestion control algorithm;

a processing unit, configured to adjust a first congestion parameter corresponding to a first application type of the first application according to the first transmission performance indicator, and the adjusted first congestion parameter is used to obtain an adjusted first congestion control algorithm, The adjusted first congestion control algorithm is used to perform congestion control on the traffic data of the first application.
The device according to claim 33, wherein when the processing unit is configured to adjust the first congestion parameter corresponding to the first application type of the first application according to the first transmission performance indicator, the processing unit is specifically configured to:

Obtaining, according to the first transmission performance indicator, a requirement of the first application for the transmission performance indicator;

The first congestion parameter is adjusted according to the requirements of the first application for transmission performance indicators.
The device according to claim 34, wherein when the processing unit is configured to adjust the first congestion parameter according to the requirements of the first application on the transmission performance indicator, the processing unit is specifically configured to:

Inputting the first transmission performance index into an objective function to obtain a first evaluation value; the objective function is used to evaluate the requirements of the first application on the transmission performance index;

Based on the first evaluation value, the first congestion parameter is adjusted.
A network device, comprising: at least one processor and a memory;

the memory stores one or more computer programs;

One or more computer programs stored in the memory, when executed by the at least one processor, cause the network device to perform the method of any one of claims 1-16.
An adjustment device, characterized in that it comprises: at least one processor and a memory;

the memory stores one or more computer programs;

One or more computer programs stored in the memory, when executed by the at least one processor, cause the adjustment device to perform the method of any of claims 17-27.
A computer storage medium, characterized in that, the computer-readable storage medium is used to store a computer program, and when the computer program is run on a computer, the computer is made to execute any one of claims 1-16. method, or causing the computer to perform the method according to any one of claims 17-27.
A network system, characterized in that it includes: adjustment equipment and network equipment;

The adjustment device is configured to obtain a first transmission performance index corresponding to the traffic data of the first application; adjust the first congestion parameter corresponding to the application type of the first application according to the first transmission performance index; sending the first congestion parameter to the network device;

The network device is configured to obtain an adjusted first congestion control algorithm according to the adjusted first congestion parameter, and perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm.
The system according to claim 39, wherein before the adjustment device is configured to acquire the first transmission performance indicator corresponding to the traffic data of the first application, the network device is further configured to:

obtaining a first application type of the first application;

obtaining the first congestion parameter according to the first application type;

obtaining a first congestion control algorithm based on the first congestion parameter;

When the adjustment device is used to obtain the first transmission performance indicator corresponding to the traffic data of the first application, it is specifically used to:

Acquire a first transmission performance indicator corresponding to when the network device performs congestion control on the traffic data of the first application based on the first congestion control algorithm.
The system according to claim 39 or 40, wherein after the network device is configured to perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm, the adjustment device is further configured to:

Acquire a second transmission performance indicator corresponding to when the network device performs congestion control on the traffic data of the first application according to the adjusted first congestion control algorithm.
A network system, characterized by comprising: identification equipment and network equipment;

the identifying device, configured to identify the first application type of the first application; sending the first application type to the network device;

The network device is configured to obtain, according to the first application type, a first congestion parameter corresponding to the first application type, where the first congestion parameter is used to obtain a first congestion control algorithm, and the first congestion control The algorithm is used to perform congestion control on the traffic data of the first application.
The system according to claim 42, wherein after the network device is configured to obtain the first congestion parameter corresponding to the first application type according to the first application type, the network device is further configured to:

obtaining the first congestion control algorithm based on the first congestion parameter;

Congestion control is performed on the traffic data of the first application based on the first congestion control algorithm.
The system of claim 43, wherein the network system further comprises an adjustment device for:

Acquire a first transmission performance index corresponding to when the network device performs congestion control on the traffic data of the first application based on the first congestion control algorithm; adjust the corresponding first application type according to the first transmission performance index The first congestion parameter of ; send the adjusted first congestion parameter to the network device;

The network equipment is used for:

Obtain an adjusted first congestion control algorithm according to the adjusted first congestion parameter, and perform congestion control on the traffic data of the first application based on the adjusted first congestion control algorithm.