CN116599908A - Internet private line speed regulation method, device, electronic equipment and medium - Google Patents

Internet private line speed regulation method, device, electronic equipment and medium Download PDF

Info

Publication number
CN116599908A
CN116599908A CN202310621499.7A CN202310621499A CN116599908A CN 116599908 A CN116599908 A CN 116599908A CN 202310621499 A CN202310621499 A CN 202310621499A CN 116599908 A CN116599908 A CN 116599908A
Authority
CN
China
Prior art keywords
line
internet
bandwidth utilization
utilization rate
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310621499.7A
Other languages
Chinese (zh)
Inventor
张超
王路
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN202310621499.7A priority Critical patent/CN116599908A/en
Publication of CN116599908A publication Critical patent/CN116599908A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/26Flow control; Congestion control using explicit feedback to the source, e.g. choke packets
    • H04L47/263Rate modification at the source after receiving feedback
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/149Network analysis or design for prediction of maintenance
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The application provides an internet private line speed regulation method, an internet private line speed regulation device, electronic equipment and a medium. The method comprises the following steps: acquiring line information of a current internet private line, wherein the line information comprises time information, bandwidth utilization rate and network quality parameters at the current moment; inputting the line information of the internet private line into a time sequence-based prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model; the prediction model is a model obtained by training in advance; and carrying out special line speed regulation on the internet special line according to the bandwidth utilization rate of the internet special line at the next moment and the bandwidth utilization rate threshold of the internet special line at the next moment. The method solves the problem that the bandwidth resources cannot be fully utilized in the traditional internet private line service.

Description

Internet private line speed regulation method and device, electronic equipment and medium
Technical Field
The present application relates to communications technologies, and in particular, to a method and apparatus for internet private line speed regulation, an electronic device, and a medium.
Background
In recent years, with the continuous appearance of novel technologies such as 5G, the traditional home-wide service tends to be saturated, the service carried by the traditional metropolitan area network has new changes, the internet private line service is gradually raised, and new requirements are also put forward. The internet private line service refers to a service of accessing a client network and equipment to the internet through a special link to provide real-time on-line internet service with various rates for clients.
The traditional internet private line provides a private line with fixed bandwidth for users, but the quality of the line is often deteriorated in the period of busy service, and the user experience is affected; the line is idle on holidays or at specific time, increasing the cost of ordering the dedicated line. Therefore, the conventional internet private line service has the problem that bandwidth resources cannot be fully utilized.
Disclosure of Invention
The application provides an internet private line speed regulation method, an internet private line speed regulation device, electronic equipment and a medium, which are used for solving the problem that the bandwidth resource cannot be fully utilized in the traditional internet private line service.
In one aspect, the application provides an internet private line speed regulation method, which comprises the following steps:
acquiring line information of a current internet private line, wherein the line information comprises time information, bandwidth utilization rate and network quality parameters at the current moment;
inputting the line information of the current internet private line into a time sequence-based prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model; the prediction model is a model obtained by training in advance;
and carrying out special line speed regulation on the internet special line according to the bandwidth utilization rate of the internet special line at the next moment and the bandwidth utilization rate threshold of the internet special line at the next moment.
In one possible implementation, the method further includes:
collecting line information according to a preset period in preset data collection time as characteristic parameters of model training, wherein the characteristic parameters comprise time information, bandwidth utilization rate and network quality parameters;
performing single-heat coding on the time information in the characteristic parameters, and splicing the time information with the corresponding characteristic parameters to obtain a model training vector;
establishing an initial model, wherein the initial model is a time sequence-based cyclic neural network model and comprises a feature extraction layer and a full connection layer;
and inputting the model training vector into the initial model, and carrying out model training on the initial model by using a loss function of a mean square error to obtain the prediction model.
In one possible implementation manner, the collecting the line information according to the predetermined period includes:
receiving line information reported by a metropolitan area network controller;
for a plurality of the line information received in each of the predetermined periods, line information in the predetermined period is obtained by averaging.
In one possible implementation manner, the inputting the line information of the current internet private line into a time sequence-based prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model includes:
Performing single-heat coding on time information in the line information of the current internet private line, and splicing the time information with the bandwidth utilization rate and the network quality parameter at the current moment to obtain a model input vector;
inputting the model input vector into a feature extraction layer of the prediction model to obtain an output feature vector corresponding to the current moment;
and inputting the feature vector into a full-connection layer of the prediction model to carry out regression prediction, so as to obtain the bandwidth utilization rate of the next moment of output.
In one possible implementation manner, the performing dedicated line speed adjustment on the internet dedicated line according to the bandwidth utilization of the internet dedicated line at the next moment and the bandwidth utilization threshold of the internet dedicated line at the next moment includes:
if the bandwidth utilization rate of the internet private line at the next moment is higher than the threshold upper limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth speed-up;
if the bandwidth utilization rate of the internet private line at the next moment is lower than the threshold lower limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth deceleration;
and if the bandwidth utilization rate of the internet private line at the next moment is between the upper limit and the lower limit of the bandwidth utilization rate threshold of the internet private line at the next moment, maintaining the current bandwidth.
On the other hand, the application provides an internet private line speed regulating device, which comprises: the system comprises an acquisition module, a network quality parameter acquisition module and a network quality parameter acquisition module, wherein the acquisition module is used for acquiring line information of a current internet private line, and the line information comprises time information, bandwidth utilization rate and the network quality parameter at the current moment;
the prediction module is used for inputting the line information of the current internet private line into a time sequence-based prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model; the prediction model is a model obtained by training in advance;
and the speed regulation module is used for carrying out special line speed regulation on the internet special line according to the bandwidth utilization rate of the internet special line at the next moment and the bandwidth utilization rate threshold of the internet special line at the next moment.
In one possible implementation, the apparatus further includes:
the training module is used for collecting line information according to a preset period in preset data collection time and taking the line information as a characteristic parameter of model training, wherein the characteristic parameter comprises time information, bandwidth utilization rate and network quality parameters;
performing single-heat coding on the time information in the characteristic parameters, and splicing the time information with the corresponding characteristic parameters to obtain a model training vector;
Establishing an initial model, wherein the initial model is a time sequence-based cyclic neural network model and comprises a feature extraction layer and a full connection layer;
and inputting the model training vector into the initial model, and carrying out model training on the initial model by using a loss function of a mean square error to obtain the prediction model.
In one possible implementation manner, the training module is specifically configured to:
receiving line information reported by a metropolitan area network controller;
for a plurality of the line information received in each of the predetermined periods, line information in the predetermined period is obtained by averaging.
In one possible implementation manner, the speed regulation module is specifically configured to:
performing single-heat coding on time information in the line information of the current internet private line, and splicing the time information with the bandwidth utilization rate and the network quality parameter at the current moment to obtain a model input vector;
inputting the model input vector into a feature extraction layer of the prediction model to obtain an output feature vector corresponding to the current moment;
and inputting the feature vector into a full-connection layer of the prediction model to carry out regression prediction, so as to obtain the bandwidth utilization rate of the next moment of output.
In one possible implementation manner, the speed regulation module is specifically configured to:
if the bandwidth utilization rate of the internet private line at the next moment is higher than the threshold upper limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth speed-up;
if the bandwidth utilization rate of the internet private line at the next moment is lower than the threshold lower limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth deceleration;
and if the bandwidth utilization rate of the internet private line at the next moment is between the upper limit and the lower limit of the bandwidth utilization rate threshold of the internet private line at the next moment, maintaining the current bandwidth.
In yet another aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively coupled to the processor; the memory stores computer-executable instructions; the processor executes computer-executable instructions stored in the memory to implement the method as described above.
In yet another aspect, the application provides a computer-readable storage medium having stored therein computer-executable instructions for performing the method as described above when executed by a processor.
According to the internet private line speed regulation method, the device, the electronic equipment and the medium, the bandwidth utilization rate of the user internet private line at the next moment is predicted by using the regression prediction model based on the cyclic neural network, and the internet private line is subjected to private line speed regulation according to the predicted bandwidth utilization rate of the internet private line at the next moment and the corresponding bandwidth utilization rate threshold value, so that the requirements of user business on speed rising in busy hours and speed reducing in idle hours are met. According to the scheme provided by the application, the AI model is used for predicting the flow of the user line and carrying out intelligent speed regulation of the internet private line, so that dynamic speed regulation according to the service requirement of the client side is realized, the line quality deterioration in the busy service period is avoided, the line is idle in the idle service period, the bandwidth resource is fully utilized, and the user experience is effectively improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic flow chart illustrating an internet private line speed regulation method according to a first embodiment of the present application;
FIG. 2 is a schematic flow chart of obtaining a prediction model according to a first embodiment of the present application;
FIG. 3 is a diagram schematically showing an exemplary structure of a prediction model according to a first embodiment of the present application;
fig. 4 is a schematic flow chart illustrating speed regulation by a user using an internet private line according to a first embodiment of the present application;
fig. 5 is a schematic structural diagram of an internet private line speed regulation device according to a second embodiment of the present application;
fig. 6 is a schematic structural diagram of an internet dedicated line speed regulation electronic device according to a third embodiment of the present application.
Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The modules in the present application refer to functional modules or logic modules. It may be in the form of software, the functions of which are implemented by the execution of program code by a processor; or may be in hardware. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
In recent years, with the continuous appearance of novel technologies such as 5G, the traditional home-wide service tends to be saturated, the service carried by the traditional metropolitan area network has new changes, the internet private line service is gradually raised, and new requirements are also put forward. The internet private line service refers to a service of accessing a client network and equipment to the internet through a special link to provide real-time on-line internet service with various rates for clients.
The traditional internet private line provides a private line with fixed bandwidth for users, but the quality of the line is often deteriorated in the period of busy service, and the user experience is affected; the line is idle on holidays or at specific time, increasing the cost of ordering the dedicated line.
Therefore, the special line speed regulation can better meet the demands of clients according to the traffic use condition of the clients, and with the development of artificial intelligence technology, the prediction of user behavior based on AI is increasingly integrated into the daily life of people. For enterprise users of the internet private line, the traffic use condition of the users in a specific time period often has a certain regularity, and the possibility is provided for training a traffic prediction model of the users.
The technical scheme of the application is illustrated in the following specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
Example 1
Fig. 1 is a flow chart of an internet private line speed regulation method according to an embodiment of the application. As shown in fig. 1, the internet private line speed regulation method provided in this embodiment may include:
s101, acquiring line information of a current internet private line, wherein the line information comprises time information, bandwidth utilization rate and network quality parameters at the current moment;
s102, inputting line information of the internet private line into a time sequence-based prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model; the prediction model is a model obtained by training in advance;
s103, carrying out special line speed regulation on the internet special line according to the bandwidth utilization rate of the internet special line at the next moment and the bandwidth utilization rate threshold of the internet special line at the next moment.
In practical application, the execution main body of the embodiment may be an internet dedicated line speed regulation device, and the device may be implemented by a computer program, for example, application software and the like; alternatively, the computer program may be implemented as a medium storing a related computer program, for example, a usb disk, a cloud disk, or the like; still alternatively, it may be implemented by a physical device, e.g., a chip, a server, etc., integrated with or installed with the relevant computer program.
Through carrying out investigation to internet private line user, can find that the line of user internet private line is busy and the line is idle often has certain time law, for example dining enterprise 11 every day: 00-14:00, 17:00-20: the 00 lines are busy, the bandwidth utilization rate is high, the user network quality is poor, the rest time lines are idle, and the user network quality is good. Therefore, the business busy and idle of a specific enterprise is regular, so that the rule can be learned through a deep learning model, and the flow prediction of the line is realized. In view of this, in this embodiment, the AI model is introduced to predict the traffic of the subscriber line, so as to determine the busy hour and the idle hour of the subscriber line, and then intelligent speed regulation is performed according to the correlation result.
Specifically, the internet private line speed regulating device obtains line information of the current internet private line, wherein the line information includes time information, bandwidth utilization rate and network quality parameters at the current moment, for example, the line information may include time, week, bandwidth utilization rate and quality of service (Quality of Service, qoS) (may include time delay, jitter, packet loss, etc.), and may be selected according to practical application conditions, which is not limited herein. Inputting the obtained line information of the current internet private line into a prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model; the prediction model is a time sequence-based recurrent neural network regression prediction model and is trained in advance.
For example, assuming that a restaurant enterprise orders an internet special line speed regulation product proposed by the scheme, the internet special line speed regulation device automatically collects line information of the internet special line of the enterprise, and inputs the line information at the current moment into a trained prediction model to obtain predicted line information at the next moment. For example, the current line information is about 10 points on Saturday, the bandwidth utilization rate is about 70%, the prediction model is input, the line information at the next time is about 11 points on Saturday, the bandwidth utilization rate is 100%, and the preset upper limit of the bandwidth utilization rate threshold is 75%, which indicates that the line will enter a busy state at the next time, and special line speed-up is performed.
In practical applications, there may be various ways to obtain the prediction model, and fig. 2 is a schematic flow chart of obtaining the prediction model according to an embodiment of the present application, and in one example, the method further includes:
s201, collecting line information according to a preset period in preset data collection time as characteristic parameters of model training, wherein the characteristic parameters comprise time information, bandwidth utilization rate and network quality parameters;
s202, performing single-heat coding on time information in the characteristic parameters, and splicing the time information with the corresponding characteristic parameters to obtain a model training vector;
S203, an initial model is established, wherein the initial model is a time sequence-based cyclic neural network model and comprises a feature extraction layer and a full connection layer;
s204, inputting the model training vector into the initial model, and performing model training on the initial model by using a loss function of a mean square error to obtain the prediction model.
Specifically, the scheme uses a time-series-based recurrent neural network model as an initial model, wherein the initial model comprises a feature extraction layer for feature extraction and a fully connected layer for regression prediction. The data acquisition time and the period are preset by a user, and the internet special line speed regulating device acquires line information according to the preset period in the preset data acquisition time so as to acquire the historical line information of the user as a characteristic parameter of model training. The characteristic parameters include, but are not limited to, time information (time, week), bandwidth utilization, network quality parameters QoS (delay, jitter, packet loss), and can be selected according to the needs of practical application. Because the time information (time and week) is discrete value and the data volume is moderate, unique coding is carried out on the time information, the value of the discrete feature is expanded to European space, and the feature analysis can be better carried out. And splicing the processed time information with other characteristic parameters to obtain a model training vector for learning a user flow using rule by the model. The model training vector is input into an initial model, and the initial model is trained by using a loss function of mean square error to obtain a prediction model in order to improve the accuracy of regression prediction.
In one example, the inputting the line information of the current internet private line into a time sequence-based prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model includes:
performing single-heat coding on time information in the line information of the current internet private line, and splicing the time information with the bandwidth utilization rate and the network quality parameter at the current moment to obtain a model input vector;
inputting the model input vector into a feature extraction layer of the prediction model to obtain an output feature vector corresponding to the current moment;
and inputting the feature vector into a full-connection layer of the prediction model to carry out regression prediction, so as to obtain the bandwidth utilization rate of the next moment of output.
Specifically, the model input vector is obtained according to the line information at the current moment, and the process of obtaining the model input vector is similar to that of the model training vector, and is not described herein. After the model input vector is input into the prediction model, the feature extraction layer performs feature extraction on the model input vector to obtain a feature vector corresponding to the current moment output by the feature extraction layer, wherein the feature vector corresponding to the current moment contains line feature information and historical feature information of the current moment. And inputting the feature vector corresponding to the current moment into the full-connection layer, and obtaining the predicted bandwidth utilization rate of the next moment output by the full-connection layer through regression prediction.
Fig. 3 is a diagram illustrating a structure of a prediction model according to an embodiment of the present application. As shown in fig. 3, it is assumed that line information is obtained by collecting states of lines used by users every one hour, including: time (0-23), week (1-7), bandwidth utilization of the user, qoS of the user (delay, jitter, packet loss). And carrying out characteristic processing on the line information at different moments: one-hot encoding (One-hot) is used for characterizing the time and day two parameters, and the user's bandwidth utilization and QoS values are data values so that no mapping is required. Splicing the processed line information at different moments to obtain different informationVector X corresponding to time i
X i =Concat[Onehot(F i ):Onehot(F week ):F Bi-1 :F QoSi-1 ]
The next time to be predicted is denoted by time t, and the current time corresponding to the next time is denoted by time t-1. i=t, then the model input vector X t The calculation formula is as follows:
X t =Concat[Onehot(F t ):Onehot(F week ):F Bt-1 :F QoSt-1 ]
similarly, according to the historical line information, a model training vector X can be obtained 0 ,X 1 ,…,X t-1
Since the bandwidth utilization of the user at the next moment needs to be predicted, a time-series cyclic neural network model is selected for modeling, wherein the cyclic neural network unit selects a gating cyclic unit (Gate Recurrent Unit, GRU). Since the final task is to perform regression prediction, the model is trained using a Loss function of Mean Square Error (MSE), the calculation formula is as follows:
Loss=MSE(o t ,F Bt )=(o i -F Bi ) 2 /n,,i=1,2,3…n
Input vector X through model t And training the obtained hidden state vector h corresponding to the current moment t-1 To obtain a feature vector h containing current input information and historical feature information t Predicting corresponding feature vector h of next time t t The calculation formula is as follows:
h t =GRU(h t-1 ,X t )
obtaining a characteristic vector h t Then, regression prediction output is carried out through the fully connected neural network, and the bandwidth utilization rate o of the next moment t is predicted t The calculation formula is as follows:
o t =MLP(h t )
wherein the MLP is a multi-layered fully connected neural network.
Finally, the AI model designed by the method is used for completing the prediction of the bandwidth utilization rate of the user at the next moment according to the historical line flow information of the user and the network state information at the current moment.
In one example, the collecting the line information according to the predetermined period includes:
receiving line information reported by a metropolitan area network controller;
for a plurality of the line information received in each of the predetermined periods, line information in the predetermined period is obtained by averaging.
The traditional internet private line carries through the IP metropolitan area network and the IPRAN network of the ground city, each ground city is provided with one IP metropolitan area network and one IPRAN, and if the national customer speed regulation is to be realized, the network management systems of all provinces are needed to be respectively connected, so that the difficulty of the speed regulation task is increased. In order to meet the intelligent speed regulation requirement of the Internet private line user, the intelligent metropolitan area network is adopted to bear the Internet private line. The intelligent metropolitan area network is a converged network of an IP metropolitan area network and an IPRAN in the local city, and the networks in all the local cities are converged into one intelligent metropolitan area network. If the speed regulation is to be realized, only the intelligent metropolitan area network SDN controller needs to be docked, so that the complexity of the intelligent speed regulation task docking is reduced; the intelligent metropolitan area network is a comprehensive SDN network, all device configurations can be issued through an intelligent metropolitan area network SDN controller, and minute-level configuration issuing can be completed. Therefore, the internet private line in the intelligent metropolitan area network has the condition of issuing the user non-perception speed regulation task.
Specifically, the collected line information is reported to an intelligent metropolitan area network SDN controller for storage and processing, and the intelligent metropolitan area network SDN controller reports the processed user line information to an internet private line speed regulating device. In each preset period, the internet special line speed regulating device can receive the line information for a plurality of times, and then average value is taken as the line information in the period. For example, the internet private line speed regulating device collects the state of the line used by the user every one hour, and the minimum granularity of the line state reported by the intelligent metropolitan area network controller is 15 minutes, so that the internet private line speed regulating device takes the average value of the four received controller report messages in each period as the line information in each hour.
In practical application, the speed regulation manner of the private line may be multiple, in an example, the performing the private line speed regulation on the internet private line according to the bandwidth utilization of the internet private line at the next moment and the bandwidth utilization threshold of the internet private line at the next moment includes:
if the bandwidth utilization rate of the internet private line at the next moment is higher than the threshold upper limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth speed-up;
If the bandwidth utilization rate of the internet private line at the next moment is lower than the threshold lower limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth deceleration;
and if the bandwidth utilization rate of the internet private line at the next moment is between the upper limit and the lower limit of the bandwidth utilization rate threshold of the internet private line at the next moment, maintaining the current bandwidth.
Specifically, the user may preset a set speed regulation rule, including: and when the speed regulation threshold is triggered, the speed regulation bandwidths for speed increase and speed reduction are carried out. Judging the relation between the bandwidth utilization rate and the upper and lower threshold values of the internet private line at the next moment according to the predicted bandwidth utilization rate of the internet private line at the next moment, if the bandwidth utilization rate is higher than the preset upper threshold value, indicating that the next moment is a busy service period, and increasing the bandwidth to the bandwidth set in the speed regulation rule; if the bandwidth utilization rate is lower than the preset threshold lower limit, indicating that the next moment is a service idle period, and slowing down the bandwidth to the bandwidth set in the speed regulation rule, wherein the line is in an idle state; if the bandwidth utilization rate is between the upper and lower limits of the preset threshold, the next time line is indicated to be good in service condition, and the original bandwidth is kept unchanged.
For example, assume that the user sets the bandwidth utilization threshold to 70% upper and 30% lower, the up-speed bandwidth to 150% of the original bandwidth, and the down-speed bandwidth to 50% of the original bandwidth. If the bandwidth utilization rate of the next time line of the user is predicted to be 90%, the bandwidth is adjusted to 150% of the original bandwidth; predicting that the bandwidth utilization rate of the next time line of the user is 20%, and adjusting the bandwidth to be 50% of the original bandwidth; and predicting that the bandwidth utilization rate of the next time line of the user is 50%, and keeping the original bandwidth unchanged.
Fig. 4 is a schematic flow chart of speed regulation by using internet private line for a user according to an embodiment of the present application. As shown in fig. 4, the user logs in from the internet private line selected for use by the service system and selects intelligent speed regulation, sets the time (minimum 15 days) for collecting data and the speed regulation rule (the upper and lower limits of the bandwidth utilization threshold for speed increase and decrease, and the speed regulation bandwidth for speed increase and speed decrease when the speed regulation threshold is triggered). And starting an intelligent training mode, and the internet private line speed regulating device acquires the reported private line state information of the user within the preset time and sends the obtained characteristic information to the AI model for training. And loading the current latest training model, collecting the historical internet private line state information of the user on the same day, sending the information into an AI model, and predicting the bandwidth utilization rate of the user at the next moment. If the predicted bandwidth utilization rate is higher than the upper threshold limit designed by the user, controlling automatic issuing of speed-up configuration, wherein the speed-up bandwidth is the bandwidth set in the user rule; if the predicted bandwidth utilization rate is lower than the threshold lower limit designed by the user, controlling automatic downlink speed-down configuration, wherein the speed-down bandwidth is preset by the user; and if the predicted bandwidth is between the upper and lower thresholds set by the user, keeping the original bandwidth unchanged.
In the internet private line speed regulation method provided by the embodiment, the bandwidth utilization rate of the user internet private line at the next moment is predicted by using the regression prediction model based on the cyclic neural network, and the private line speed regulation is performed on the internet private line according to the predicted bandwidth utilization rate of the internet private line at the next moment and the corresponding bandwidth utilization rate threshold value, so that the requirements of user business on speed rising in busy hours and speed reducing in idle hours are met. According to the scheme provided by the application, the AI model is used for predicting the flow of the user line and carrying out intelligent speed regulation of the internet private line, so that dynamic speed regulation according to the service requirement of the client side is realized, the line quality deterioration in the busy service period is avoided, the line is idle in the idle service period, the bandwidth resource is fully utilized, and the user experience is effectively improved.
Example two
Fig. 5 is a schematic structural diagram of an internet dedicated line speed regulating device according to an embodiment of the present application. As shown in fig. 5, the internet private line speed regulating device provided in this embodiment may include:
the acquiring module 51 is configured to acquire line information of a current internet private line, where the line information includes time information, bandwidth utilization and network quality parameters at a current moment;
The prediction module 52 is configured to input line information of the dedicated internet line to a time sequence-based prediction model, and obtain a bandwidth utilization rate of the dedicated internet line at a next moment output by the prediction model; the prediction model is a model obtained by training in advance;
and the speed regulating module 53 is configured to regulate the speed of the dedicated internet line according to the bandwidth utilization of the dedicated internet line at the next moment and the bandwidth utilization threshold of the dedicated internet line at the next moment.
In practical application, the internet private line speed regulating device can be realized by a computer program, for example, application software and the like; alternatively, the computer program may be implemented as a medium storing a related computer program, for example, a usb disk, a cloud disk, or the like; still alternatively, it may be implemented by a physical device, e.g., a chip, a server, etc., integrated with or installed with the relevant computer program.
Through carrying out investigation to internet private line user, can find that the line of user internet private line is busy and the line is idle often has certain time law, for example dining enterprise 11 every day: 00-14:00, 17:00-20: the 00 lines are busy, the bandwidth utilization rate is high, the user network quality is poor, the rest time lines are idle, and the user network quality is good. Therefore, the business busy and idle of a specific enterprise is regular, so that the rule can be learned through a deep learning model, and the flow prediction of the line is realized. In view of this, in this embodiment, the AI model is introduced to predict the traffic of the subscriber line, so as to determine the busy hour and the idle hour of the subscriber line, and then intelligent speed regulation is performed according to the correlation result.
Specifically, the internet private line speed regulating device obtains line information of the current internet private line, wherein the line information includes time information, bandwidth utilization rate and network quality parameters at the current moment, for example, the line information may include time, week, bandwidth utilization rate and quality of service (Quality of Service, qoS) (may include time delay, jitter, packet loss, etc.), and may be selected according to practical application conditions, which is not limited herein. Inputting the obtained line information of the current internet private line into a prediction model to obtain the bandwidth utilization rate of the internet private line at the next moment output by the prediction model; the prediction model is a time sequence-based recurrent neural network regression prediction model and is trained in advance.
In practical applications, the selection of the prediction model may be various, and in one example, the apparatus further includes:
the training module is used for collecting line information according to a preset period in preset data collection time and taking the line information as a characteristic parameter of model training, wherein the characteristic parameter comprises time information, bandwidth utilization rate and network quality parameters;
performing single-heat coding on the time information in the characteristic parameters, and splicing the time information with the corresponding characteristic parameters to obtain a model training vector;
Establishing an initial model, wherein the initial model is a time sequence-based cyclic neural network model and comprises a feature extraction layer and a full connection layer;
and inputting the model training vector into the initial model, and carrying out model training on the initial model by using a loss function of a mean square error to obtain the prediction model.
Specifically, the scheme uses a time-series-based recurrent neural network model as an initial model, wherein the initial model comprises a feature extraction layer for feature extraction and a fully connected layer for regression prediction. The data acquisition time and the period are preset by a user, and the internet special line speed regulating device acquires line information according to the preset period in the preset data acquisition time so as to acquire the historical line information of the user as a characteristic parameter of model training. The characteristic parameters include, but are not limited to, time information (time, week), bandwidth utilization, network quality parameters QoS (delay, jitter, packet loss), and can be selected according to the needs of practical application. Because the time information (time and week) is discrete value and the data volume is moderate, unique coding is carried out on the time information, the value of the discrete feature is expanded to European space, and the feature analysis can be better carried out. And splicing the processed time information with other characteristic parameters to obtain a model training vector for learning a user flow using rule by the model. The model training vector is input into an initial model, and the initial model is trained by using a loss function of mean square error to obtain a prediction model in order to improve the accuracy of regression prediction.
In one example, the prediction module 52 is specifically configured to:
performing single-heat coding on time information in the line information of the current internet private line, and splicing the time information with the bandwidth utilization rate and the network quality parameter at the current moment to obtain a model input vector;
inputting the model input vector into a feature extraction layer of the prediction model to obtain an output feature vector corresponding to the current moment;
and inputting the feature vector into a full-connection layer of the prediction model to carry out regression prediction, so as to obtain the bandwidth utilization rate of the next moment of output.
Specifically, the model input vector is obtained according to the line information at the current moment, and the process of obtaining the model input vector is similar to that of the model training vector, and is not described herein. After the model input vector is input into the prediction model, the feature extraction layer performs feature extraction on the model input vector to obtain a feature vector corresponding to the current moment output by the feature extraction layer, wherein the feature vector corresponding to the current moment contains line feature information and historical feature information of the current moment. And inputting the feature vector corresponding to the current moment into the full-connection layer, and obtaining the predicted bandwidth utilization rate of the next moment output by the full-connection layer through regression prediction.
In one example, the training module is specifically configured to:
receiving line information reported by a metropolitan area network controller;
for a plurality of the line information received in each of the predetermined periods, line information in the predetermined period is obtained by averaging.
The traditional internet private line carries through the IP metropolitan area network and the IPRAN network of the ground city, each ground city is provided with one IP metropolitan area network and one IPRAN, and if the national customer speed regulation is to be realized, the network management systems of all provinces are needed to be respectively connected, so that the difficulty of the speed regulation task is increased. In order to meet the intelligent speed regulation requirement of the Internet private line user, the intelligent metropolitan area network is adopted to bear the Internet private line. The intelligent metropolitan area network is a converged network of an IP metropolitan area network and an IPRAN in the local city, and the networks in all the local cities are converged into one intelligent metropolitan area network. If the speed regulation is to be realized, only the intelligent metropolitan area network SDN controller needs to be docked, so that the complexity of the intelligent speed regulation task docking is reduced; the intelligent metropolitan area network is a comprehensive SDN network, all device configurations can be issued through an intelligent metropolitan area network SDN controller, and minute-level configuration issuing can be completed. Therefore, the internet private line in the intelligent metropolitan area network has the condition of issuing the user non-perception speed regulation task.
Specifically, the collected line information is reported to an intelligent metropolitan area network SDN controller for storage and processing, and the intelligent metropolitan area network SDN controller reports the processed user line information to an internet private line speed regulating device. In each preset period, the internet special line speed regulating device can receive the line information for a plurality of times, and then average value is taken as the line information in the period.
In practical applications, there may be various ways of speed regulation of the dedicated line, and in one example, the speed regulation module 53 is specifically configured to:
if the bandwidth utilization rate of the internet private line at the next moment is higher than the threshold upper limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth speed-up;
if the bandwidth utilization rate of the internet private line at the next moment is lower than the threshold lower limit of the bandwidth utilization rate of the internet private line at the next moment, executing bandwidth deceleration;
and if the bandwidth utilization rate of the internet private line at the next moment is between the upper limit and the lower limit of the bandwidth utilization rate threshold of the internet private line at the next moment, maintaining the current bandwidth.
Specifically, the user may preset a set speed regulation rule, including: and when the speed regulation threshold is triggered, the speed regulation bandwidths for speed increase and speed reduction are carried out. Judging the relation between the bandwidth utilization rate and the upper and lower threshold values of the internet private line at the next moment according to the predicted bandwidth utilization rate of the internet private line at the next moment, if the bandwidth utilization rate is higher than the preset upper threshold value, indicating that the next moment is a busy service period, and increasing the bandwidth to the bandwidth set in the speed regulation rule; if the bandwidth utilization rate is lower than the preset threshold lower limit, indicating that the next moment is a service idle period, and slowing down the bandwidth to the bandwidth set in the speed regulation rule, wherein the line is in an idle state; if the bandwidth utilization rate is between the upper and lower limits of the preset threshold, the next time line is indicated to be good in service condition, and the original bandwidth is kept unchanged.
In the internet private line speed regulating device provided by the embodiment, the bandwidth utilization rate of the user internet private line at the next moment is predicted by using the regression prediction model based on the cyclic neural network, and the internet private line is subjected to private line speed regulation according to the predicted bandwidth utilization rate of the internet private line at the next moment and the corresponding bandwidth utilization rate threshold value, so that the requirements of user business on speed rising in busy hours and speed reducing in idle hours are met. According to the scheme provided by the application, the AI model is used for predicting the flow of the user line and carrying out intelligent speed regulation of the internet private line, so that dynamic speed regulation according to the service requirement of the client side is realized, the line quality deterioration in the busy service period is avoided, the line is idle in the idle service period, the bandwidth resource is fully utilized, and the user experience is effectively improved.
Example III
Fig. 6 is a schematic structural diagram of an electronic device provided in an embodiment of the disclosure, as shown in fig. 6, where the electronic device includes:
a processor 291, the electronic device further comprising a memory 292; a communication interface (Communication Interface) 293 and bus 294 may also be included. The processor 291, the memory 292, and the communication interface 293 may communicate with each other via the bus 294. Communication interface 293 may be used for information transfer. The processor 291 may call logic instructions in the memory 292 to perform the methods of the above-described embodiments.
Further, the logic instructions in memory 292 described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product.
The memory 292 is a computer-readable storage medium that may be used to store a software program, a computer-executable program, and program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The processor 291 executes functional applications and data processing by running software programs, instructions and modules stored in the memory 292, i.e., implements the methods of the method embodiments described above.
Memory 292 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the terminal device, etc. Further, memory 292 may include high-speed random access memory, and may also include non-volatile memory.
The disclosed embodiments provide a non-transitory computer readable storage medium having stored therein computer-executable instructions that, when executed by a processor, are configured to implement the method of the previous embodiments.
Example IV
The disclosed embodiments provide a computer program product comprising a computer program which, when executed by a processor, implements the method provided by any of the embodiments of the disclosure described above.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (12)

1.一种互联网专线调速方法,其特征在于,包括:1. A method for speed regulation of an Internet dedicated line, characterized in that, comprising: 获取当前互联网专线的线路信息,所述线路信息包括当前时刻的时间信息、带宽利用率以及网络质量参数;Obtaining the line information of the current Internet dedicated line, the line information including time information, bandwidth utilization and network quality parameters at the current moment; 将所述当前互联网专线的线路信息输入至基于时序的预测模型,得到所述预测模型输出的下一时刻所述互联网专线的带宽利用率;其中,所述预测模型为预先训练得到的模型;Inputting the line information of the current Internet dedicated line into a time-series-based prediction model to obtain the bandwidth utilization rate of the Internet dedicated line at the next moment output by the prediction model; wherein the prediction model is a pre-trained model; 根据所述下一时刻所述互联网专线的带宽利用率和所述下一时刻下该互联网专线的带宽利用率阈值,对所述互联网专线进行专线调速。According to the bandwidth utilization rate of the Internet dedicated line at the next moment and the threshold value of the bandwidth utilization rate of the Internet dedicated line at the next moment, perform dedicated line speed regulation on the Internet dedicated line. 2.根据权利要求1所述的方法,其特征在于,所述方法还包括:2. The method according to claim 1, characterized in that the method further comprises: 在预定的数据采集时间内,按照预定周期采集线路信息,作为模型训练的特征参数,所述特征参数包括时间信息、带宽利用率以及网络质量参数;Within the predetermined data collection time, line information is collected according to a predetermined cycle as characteristic parameters for model training, and the characteristic parameters include time information, bandwidth utilization and network quality parameters; 对所述特征参数中的时间信息进行独热编码,并与对应的特征参数进行拼接,得到模型训练向量;Carrying out one-hot encoding to the time information in the characteristic parameters, and splicing with the corresponding characteristic parameters to obtain the model training vector; 建立初始模型,所述初始模型为基于时序的循环神经网络模型,包括特征提取层以及全连接层;An initial model is established, the initial model is a time series-based recurrent neural network model, including a feature extraction layer and a fully connected layer; 将所述模型训练向量输入所述初始模型,并使用均方误差的损失函数,对所述初始模型进行模型训练,得到所述预测模型。Inputting the model training vector into the initial model, and using a mean square error loss function to perform model training on the initial model to obtain the prediction model. 3.根据权利要求2所述的方法,其特征在于,所述按照预定周期采集线路信息,包括:3. The method according to claim 2, wherein the collecting line information according to a predetermined cycle comprises: 接收城域网控制器上报的线路信息;Receive line information reported by the MAN controller; 针对每个所述预定周期内接收到的多个所述线路信息,通过求平均值获得该预定周期下的线路信息。For the multiple pieces of line information received in each predetermined period, the line information in the predetermined period is obtained by averaging. 4.根据权利要求2所述的方法,其特征在于,所述将所述当前互联网专线的线路信息输入至基于时序的预测模型,得到所述预测模型输出的下一时刻所述互联网专线的带宽利用率,包括:4. The method according to claim 2, wherein the line information of the current Internet dedicated line is input into a time series-based prediction model to obtain the bandwidth of the Internet dedicated line at the next moment output by the prediction model Utilization, including: 对所述当前互联网专线的线路信息中的时间信息进行独热编码,并与当前时刻的带宽利用率和网络质量参数进行拼接,得到模型输入向量;Carrying out one-hot encoding to the time information in the line information of the current Internet dedicated line, and splicing with the bandwidth utilization rate and network quality parameters at the current moment to obtain the model input vector; 将模型输入向量输入所述预测模型的特征提取层,得到输出的当前时刻对应的特征向量;Inputting the model input vector into the feature extraction layer of the prediction model to obtain a feature vector corresponding to the current moment of output; 将所述特征向量输入所述预测模型的全连接层进行回归预测,得到输出的下一时刻的带宽利用率。The feature vector is input into the fully connected layer of the prediction model for regression prediction, and the output bandwidth utilization rate at the next moment is obtained. 5.根据权利要求1-4任一项所述的方法,其特征在于,所述根据所述下一时刻所述互联网专线的带宽利用率和所述下一时刻下该互联网专线的带宽利用率阈值,对所述互联网专线进行专线调速,包括:5. The method according to any one of claims 1-4, characterized in that, according to the bandwidth utilization rate of the Internet dedicated line at the next moment and the bandwidth utilization rate of the Internet dedicated line at the next moment Threshold, to perform dedicated line speed regulation on the Internet dedicated line, including: 若所述下一时刻所述互联网专线的带宽利用率高于所述下一时刻下该互联网专线的带宽利用率的阈值上限,则执行带宽升速;If the bandwidth utilization rate of the Internet leased line at the next moment is higher than the upper threshold of the bandwidth utilization rate of the Internet leased line at the next moment, bandwidth acceleration is performed; 若所述下一时刻所述互联网专线的带宽利用率低于所述下一时刻下该互联网专线的带宽利用率的阈值下限,则执行带宽降速;If the bandwidth utilization rate of the Internet leased line at the next moment is lower than the lower threshold of the bandwidth utilization rate of the Internet leased line at the next moment, bandwidth deceleration is performed; 若所述下一时刻所述互联网专线的带宽利用率位于所述下一时刻下该互联网专线的带宽利用率阈值上下限之间,则保持当前的带宽。If the bandwidth utilization rate of the Internet dedicated line at the next moment is between the upper and lower thresholds of the bandwidth utilization rate of the Internet dedicated line at the next moment, the current bandwidth is maintained. 6.一种互联网专线调速装置,其特征在于,包括:6. An Internet dedicated line speed regulating device, characterized in that it comprises: 获取模块,用于获取当前互联网专线的线路信息,所述线路信息包括当前时刻的时间信息、带宽利用率以及网络质量参数;An acquisition module, configured to acquire the line information of the current Internet dedicated line, the line information including time information, bandwidth utilization and network quality parameters at the current moment; 预测模块,用于将所述当前互联网专线的线路信息输入至基于时序的预测模型,得到所述预测模型输出的下一时刻所述互联网专线的带宽利用率;其中,所述预测模型为预先训练得到的模型;A prediction module, configured to input the line information of the current Internet dedicated line into a time-series-based prediction model to obtain the bandwidth utilization rate of the Internet dedicated line at the next moment output by the prediction model; wherein, the prediction model is pre-trained the resulting model; 调速模块,用于根据所述下一时刻所述互联网专线的带宽利用率和所述下一时刻下该互联网专线的带宽利用率阈值,对所述互联网专线进行专线调速。The speed regulating module is configured to regulate the speed of the Internet private line according to the bandwidth utilization rate of the Internet private line at the next moment and the bandwidth utilization threshold of the Internet private line at the next moment. 7.根据权利要求6所述的装置,其特征在于,所述装置还包括:7. The device according to claim 6, further comprising: 训练模块,用于在预定的数据采集时间内,按照预定周期采集线路信息,作为模型训练的特征参数,所述特征参数包括时间信息、带宽利用率以及网络质量参数;The training module is used to collect line information according to a predetermined cycle within a predetermined data collection time, as a characteristic parameter for model training, and the characteristic parameter includes time information, bandwidth utilization and network quality parameters; 对所述特征参数中的时间信息进行独热编码,并与对应的特征参数进行拼接,得到模型训练向量;Carrying out one-hot encoding to the time information in the characteristic parameters, and splicing with the corresponding characteristic parameters to obtain the model training vector; 建立初始模型,所述初始模型为基于时序的循环神经网络模型,包括特征提取层以及全连接层;An initial model is established, the initial model is a time series-based recurrent neural network model, including a feature extraction layer and a fully connected layer; 将所述模型训练向量输入所述初始模型,并使用均方误差的损失函数,对所述初始模型进行模型训练,得到所述预测模型。Inputting the model training vector into the initial model, and using a mean square error loss function to perform model training on the initial model to obtain the prediction model. 8.根据权利要求7所述的装置,其特征在于,所述训练模块,具体用于:8. The device according to claim 7, wherein the training module is specifically used for: 接收城域网控制器上报的线路信息;Receive line information reported by the MAN controller; 针对每个所述预定周期内接收到的多个所述线路信息,通过求平均值获得该预定周期下的线路信息。For the multiple pieces of line information received in each predetermined period, the line information in the predetermined period is obtained by averaging. 9.根据权利要求7所述的装置,其特征在于,所述调速模块,具体用于:9. The device according to claim 7, wherein the speed regulating module is specifically used for: 对所述当前互联网专线的线路信息中的时间信息进行独热编码,并与当前时刻的带宽利用率和网络质量参数进行拼接,得到模型输入向量;Carrying out one-hot encoding to the time information in the line information of the current Internet dedicated line, and splicing with the bandwidth utilization rate and network quality parameters at the current moment to obtain the model input vector; 将模型输入向量输入所述预测模型的特征提取层,得到输出的当前时刻对应的特征向量;Inputting the model input vector into the feature extraction layer of the prediction model to obtain a feature vector corresponding to the current moment of output; 将所述特征向量输入所述预测模型的全连接层进行回归预测,得到输出的下一时刻的带宽利用率。The feature vector is input into the fully connected layer of the prediction model for regression prediction, and the output bandwidth utilization rate at the next moment is obtained. 10.根据权利要求6-9任一项所述的装置,其特征在于,所述调速模块,具体用于:10. The device according to any one of claims 6-9, characterized in that the speed regulation module is specifically used for: 若所述下一时刻所述互联网专线的带宽利用率高于所述下一时刻下该互联网专线的带宽利用率的阈值上限,则执行带宽升速;If the bandwidth utilization rate of the Internet leased line at the next moment is higher than the upper threshold of the bandwidth utilization rate of the Internet leased line at the next moment, bandwidth acceleration is performed; 若所述下一时刻所述互联网专线的带宽利用率低于所述下一时刻下该互联网专线的带宽利用率的阈值下限,则执行带宽降速;If the bandwidth utilization rate of the Internet leased line at the next moment is lower than the lower threshold of the bandwidth utilization rate of the Internet leased line at the next moment, bandwidth deceleration is performed; 若所述下一时刻所述互联网专线的带宽利用率位于所述下一时刻下该互联网专线的带宽利用率阈值上下限之间,则保持当前的带宽。If the bandwidth utilization rate of the Internet dedicated line at the next moment is between the upper and lower thresholds of the bandwidth utilization rate of the Internet dedicated line at the next moment, the current bandwidth is maintained. 11.一种电子设备,其特征在于,包括:处理器,以及与所述处理器通信连接的存储器;11. An electronic device, comprising: a processor, and a memory communicatively connected to the processor; 所述存储器存储计算机执行指令;the memory stores computer-executable instructions; 所述处理器执行所述存储器存储的计算机执行指令,以实现如权利要求1-5中任一项所述的方法。The processor executes the computer-implemented instructions stored in the memory to implement the method according to any one of claims 1-5. 12.一种计算机可读存储介质,其特征在于,所述计算机可读存储介质中存储有计算机执行指令,所述计算机执行指令被处理器执行时用于实现如权利要求1-5中任一项所述的方法。12. A computer-readable storage medium, characterized in that, computer-executable instructions are stored in the computer-readable storage medium, and the computer-executable instructions are used to implement any one of claims 1-5 when executed by a processor. method described in the item.
CN202310621499.7A 2023-05-29 2023-05-29 Internet private line speed regulation method, device, electronic equipment and medium Pending CN116599908A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310621499.7A CN116599908A (en) 2023-05-29 2023-05-29 Internet private line speed regulation method, device, electronic equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310621499.7A CN116599908A (en) 2023-05-29 2023-05-29 Internet private line speed regulation method, device, electronic equipment and medium

Publications (1)

Publication Number Publication Date
CN116599908A true CN116599908A (en) 2023-08-15

Family

ID=87595406

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310621499.7A Pending CN116599908A (en) 2023-05-29 2023-05-29 Internet private line speed regulation method, device, electronic equipment and medium

Country Status (1)

Country Link
CN (1) CN116599908A (en)

Similar Documents

Publication Publication Date Title
CN108924221B (en) Method and apparatus for allocating resources
CN109271015B (en) Method for reducing energy consumption of large-scale distributed machine learning system
US11652720B2 (en) Allocating cloud resources in accordance with predicted deployment growth
CN110990138B (en) Resource scheduling method, device, server and storage medium
CN110351571A (en) Live video cloud transcoding resource allocation and dispatching method based on deeply study
US11632713B2 (en) Network capability exposure method and device thereof
CN110519783A (en) 5G network based on enhancing study is sliced resource allocation methods
CN113543160B (en) 5G slice resource allocation method, device, computing equipment and computer storage medium
CN113778691B (en) Task migration decision method, device and system
CN114845400A (en) Flexe-based resource allocation method and system
CN107566535A (en) Adaptive load balancing strategy based on user concurrent access timing planning in a kind of web map service
CN114158073B (en) Network slice deployment method, device, equipment and storage medium
CN118759871A (en) Main control equipment, home appliance computing equipment, distributed systems
CN117082008B (en) Virtual elastic network data transmission scheduling method, computer device and storage medium
CN116599908A (en) Internet private line speed regulation method, device, electronic equipment and medium
CN117472506A (en) A predictive containerized edge application autoscaler and method
CN117499997A (en) Space-time data driven electric power 5G slice resource cooperative adjustment method and system
CN114153612B (en) A CPU resource dynamic allocation method to improve the overall system throughput
CN117573339A (en) Dynamic capacity expansion and contraction method, device and storage medium for satellite edge computing services
CN117290720A (en) Individualized federal multi-task learning method for power terminal and related equipment
CN115562841A (en) Cloud video service self-adaptive resource scheduling system and method
CN117149382A (en) Virtual machine scheduling method, device, computer equipment and storage medium
CN114650297B (en) A self-adaptive auto-scaling method and system in a multi-microservice calling environment
Preetham et al. Resource provisioning in cloud using ARIMA and LSTM technique
CN115225478B (en) Network slice dynamic configuration method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination