WO2019075642A1 - 一种网络路径优化方法、系统、控制服务端以及入网端 - Google Patents

一种网络路径优化方法、系统、控制服务端以及入网端 Download PDF

Info

Publication number
WO2019075642A1
WO2019075642A1 PCT/CN2017/106577 CN2017106577W WO2019075642A1 WO 2019075642 A1 WO2019075642 A1 WO 2019075642A1 CN 2017106577 W CN2017106577 W CN 2017106577W WO 2019075642 A1 WO2019075642 A1 WO 2019075642A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
parameter
optimal
optimal path
network
Prior art date
Application number
PCT/CN2017/106577
Other languages
English (en)
French (fr)
Inventor
庄光涛
Original Assignee
深圳前海达闼云端智能科技有限公司
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 深圳前海达闼云端智能科技有限公司 filed Critical 深圳前海达闼云端智能科技有限公司
Priority to CN201780002591.8A priority Critical patent/CN108064439B/zh
Priority to PCT/CN2017/106577 priority patent/WO2019075642A1/zh
Publication of WO2019075642A1 publication Critical patent/WO2019075642A1/zh
Priority to US16/783,476 priority patent/US11146482B2/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0803—Configuration setting
    • H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0823—Errors, e.g. transmission errors
    • H04L43/0829—Packet loss
    • H04L43/0835—One way packet loss
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0852—Delays
    • H04L43/0858—One way delays
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/22—Alternate routing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/302—Route determination based on requested QoS
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/302—Route determination based on requested QoS
    • H04L45/306—Route determination based on the nature of the carried application
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/50—Routing or path finding of packets in data switching networks using label swapping, e.g. multi-protocol label switch [MPLS]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/16—Threshold monitoring

Definitions

  • the present application relates to the field of Application Delivery Network (ADN), and specifically relates to a network path optimization method, system, control server, and network access terminal based on data analysis.
  • ADN Application Delivery Network
  • ADN Application Delivery Network
  • the optimal path selection is based on the network delay and packet loss rate of real-time detection, and the path selection is performed by the shortest path algorithm.
  • the detection data will judge the current path network status according to the current detection data every minute, and decide whether to switch the path, and no reference historical data.
  • the calculated optimal path is likely to be unstable after the link.
  • the path that the access passes is the path selected according to the optimal path algorithm. Due to the complicated network conditions, the network status between two adjacent devices in the optimal path may be in a state where the fault cannot be linked or may cause a link error. Information, therefore, the optimal path of the prior art cannot accurately reflect the true link path and cannot accurately reflect the historical path condition.
  • the present application provides a network path optimization method, system, control server, and network access terminal, the network path optimization method and the system provide an optimal path in response to a user request, and according to the real path of the network access end Identifying parameter changes with the optimal path, adding a modifiable tag, such as a node status, dynamically updating the optimal path based on the parameter change and the tag, thereby reducing the switching frequency of the link path and making the network link more stable.
  • a modifiable tag such as a node status
  • an embodiment of the present application provides a network path optimization method, including the following steps:
  • the optimal path and the path parameter are updated according to the parameter change.
  • the embodiment of the present application provides a network path optimization method, including the following steps:
  • the optimal path and the path parameter are updated according to the parameter change.
  • the embodiment of the present application provides a network path optimization method, including the following steps:
  • the embodiment of the present application provides a network path optimization method, including the following steps:
  • the embodiment of the present application further provides a network path optimization system, including a control service.
  • a network path optimization system including a control service.
  • a plurality of network access terminals and a data processing terminal cluster the plurality of network access network networks, the plurality of network access terminals are in communication with the control server and the data processing terminal cluster, and the control server is communicatively connected to the data processing terminal cluster;
  • the control server is configured to calculate and send an optimal path with path coding and path parameters in response to the network access request;
  • the network access end is configured to add a path label to the optimal path according to the real path;
  • the data processing terminal cluster is configured to determine a parameter change between the optimal path and the real path based on the path parameter and the path label;
  • the control server is further configured to update the optimal path and the path parameter according to the parameter change.
  • the sixth aspect is illustrated by the single processing terminal.
  • the embodiment of the present application provides a control server, including an allocation module, an obtaining module, and an adjusting module:
  • the allocation module is configured to calculate and send an optimal path with path coding and path parameters in response to the network access request;
  • the acquiring module is configured to acquire a parameter change of an optimal path and a real path based on the path parameter and the path label, where the path label is added to the optimal path according to the real path;
  • the adjustment module is configured to update the optimal path and the path parameter according to the parameter change.
  • the seventh aspect is illustrated by the single processing terminal.
  • the embodiment of the present application provides a network access terminal, including a receiving module, a label module, and a transmitting module.
  • the receiving module is configured to receive an optimal path with path coding and path parameters calculated in response to the network access request;
  • the tag module is configured to add a path label to the optimal path according to a real path
  • the transmitting module is configured to upload the optimal path of the added path label to the data processing terminal cluster, and the data processing terminal cluster determines the parameter change of the optimal path and the real path based on the path parameter and the path label;
  • the receiving module is further configured to receive an optimal path and a path parameter updated according to the parameter change.
  • the eighth aspect is illustrated by the single processing terminal.
  • the embodiment of the present application provides a data processing terminal, including a receiving module, an extracting module, an analyzing module, and an interface module.
  • the receiving module is configured to receive an optimal path with path coding and path parameters calculated in response to the network access request;
  • the extraction module is configured to obtain a path label added to the optimal path according to a real path
  • the analyzing module is configured to determine a parameter change of the optimal path and the real path based on the path parameter and the path label, where the parameter change is used to update the optimal path;
  • the interface module is configured to transmit the parameter change to be stored.
  • the embodiment of the present application further provides an electronic device, including:
  • At least one processor and,
  • the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to establish a data channel through the communication component to enable the at least one processor to perform the method as described above.
  • the embodiment of the present application further provides a non-transitory computer readable storage medium, where the computer-readable storage medium is stored, where the computer-executable instructions are used to cause a computer to execute the above The method described.
  • the embodiment of the present application further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions When the program instructions are executed by a computer, the computer is caused to perform the method as described above.
  • the application of the present invention provides a network path optimization method, a system, a control server, and a network access terminal.
  • the network path optimization method and the system provide an optimal path in response to a user request, and add a label according to the real path of the network access terminal. And establishing a history log according to the label, identifying an average delay rate and a packet loss rate or an error code and other parameters and conditions between the nodes based on the history log, for updating the optimal path, reducing the switching frequency of the link path, and making the network link more
  • the network path optimization method and the control server of the system obtain the changed parameters of the encoded optimal path, and the control server adjusts the path parameters of the optimal path according to the change parameter and the label, such as the error rate. For example, the path weight of the node and the time for calculating the optimal path to adjust the optimal path selection, or adjust the weight between the two nodes on the optimal path to achieve optimal path dynamic adjustment.
  • FIG. 1 is a system architecture diagram of a network path optimization system provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of an optimal path of a network path optimization system according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of a real path of a network path optimization system according to an embodiment of the present application.
  • FIG. 4 is a main flowchart of a network path optimization method provided by an embodiment of the present application.
  • FIG. 5 is a flowchart of a control server of a network path optimization method according to an embodiment of the present application
  • FIG. 6 is a flowchart of a network access end of a network path optimization method according to an embodiment of the present application
  • FIG. 7 is a flowchart of a data processing terminal of a network path optimization method according to an embodiment of the present application.
  • FIG. 8 is a block diagram of a control server module of a network path optimization system according to an embodiment of the present application.
  • FIG. 9 is a block diagram of a network access end of a network path optimization system according to an embodiment of the present application.
  • FIG. 10 is a block diagram of a data processing terminal of a network path optimization system according to an embodiment of the present application.
  • FIG. 11 is a hardware framework diagram of a method for implementing network path optimization according to an embodiment of the present application.
  • the network path optimization method and system provided by the embodiment of the present application provide a dynamically adjusted optimal path in response to a user request, and add a label according to a parameter change between the real path and the optimal path when the network access terminal accesses, and establish a history log to The optimal path is dynamically updated based on parameter changes and tags, thereby reducing the switching frequency of the link path and making the network link more stable.
  • the network path optimization method and system are applied to an Application Delivery Network (ADN), and a network optimization server cluster is established, including an application delivery network 20, a control server 10, and a large network.
  • ADN Application Delivery Network
  • the network path optimization system encodes the calculated optimal path, adds path parameters and adds event tags, based on the division of the server device, controls the server 10 as a processing center, accelerates the establishment of the access path link, and reduces the link path switching. Frequency makes network links more stable.
  • the application delivery network 20 is composed of a plurality of network access terminals 20-1, network access terminals 20-2, network access terminals 20-3, and network access terminals 20-n.
  • the access terminals are the access points of the application delivery network 20, and the access points are located at the side of the network. Outside the edge, access to the internal network, the Internet Service Provider (ISP) provides services through the network access, including Internet access, wide-area connectivity or telephone service (PSTN).
  • PSTN wide-area connectivity or telephone service
  • the incoming end (POP side) provides links to services and sites.
  • the access point is a point of access to the Internet from one place to another.
  • a typical Internet Service Provider (ISP) or online service provider has one or several access points on the Internet.
  • the number of outlets owned by Internet Service Providers can be used as a measure of size and growth rate.
  • the network access terminal may be a standalone server node or a leased space installed in a telecommunication carrier.
  • the network access terminal generally includes a router, a server, and the like.
  • the data processing terminal cluster 30 receives the optimal path in the big data processing manner and the path label added by the application delivery network 20 to the optimal path to extract the information of the real path and the updated reference data into the optimal path.
  • the network path optimization system of this embodiment includes a control server 10, a plurality of network access terminals 20-1 to 20-n, a data storage server 40, an interface server 50, and a data processing terminal cluster 30- 1 to 30-n.
  • the networking of the plurality of access terminals 20-1 to 20-n becomes an application delivery network.
  • the plurality of access terminals 20-1 to 20-n are connected to a control server, and the plurality of network terminals 20-1 to 20-n are communicatively coupled to the data processing terminal clusters 30-1 to 30-n.
  • the control server 10 is communicatively coupled to the data processing terminal clusters 30-1 through 30-n.
  • the parameter change data generated by the data processing terminal clusters 30-1 to 30-n is sent to the data storage server 40 for storage, and the control server 10 periodically requests the interface server 50 for the path parameters and parameter changes of the optimal path.
  • the path label and the production history log added by the network access terminals 20-1 to 20-n are stored in the data processing terminal clusters 30-1 to 30-n, and the calculated parameter change result is stored in the data storage server 40. Modifying and adjusting the optimal path according to the path parameter and the parameter change.
  • the control server 10 calculates an optimal path with a path code and a path parameter in response to the network access request, and sends the optimal path information to the network access end of the application delivery network 20 that receives the network access request.
  • the network access terminal 20-1 is also sent to the data processing terminal clusters 30-1 to 30-n.
  • the network access terminal 20-1 After the network access terminal 20-1 receives the optimal path with path coding and path parameters, according to the optimal The path establishes a link and adds a path label to the received optimal path according to the link status of the real path, such as an average delay rate and a packet loss rate or an error code between the nodes.
  • the data processing terminal clusters 30-1 to 30-n determine parameter changes between the optimal path and the real path based on the path parameter and the path label.
  • the data processing terminal clusters 30-1 to 30-n are communicatively coupled to the data storage server 40.
  • the data storage server 40 stores calculation results of the data processing terminal clusters 30-1 to 30-n, such as parameter changes.
  • the control server 10 changes and updates the optimal path according to the parameter, thereby providing a stable and fast connection link consistent with the network condition for the user request.
  • control server includes an allocation module 12 , an acquisition module 14 , and an adjustment module 16 .
  • the optimal path ends with a number of access nodes from the user terminal 60 passing through the application delivery network 20 to the access source station 70, including a plurality of nodes.
  • the path parameter is a path weight of the node and an optimal path calculation time, wherein the data processing terminal cluster is further configured to analyze a correlation parameter state such as a delay rate or a packet loss rate between the nodes of the optimal path. And parameter changes to determine the node status.
  • control server In network path optimization, the role of the control server is:
  • the obtaining module 14 acquires a parameter change of the optimal path and the real path based on the path parameter and the path label analysis, and the path label is added to the optimal path according to the real path.
  • the adjustment module 16 changes and updates the optimal path according to the parameter.
  • the optimal path generally includes multiple nodes.
  • the path parameter is a path weight of the node and an optimal path calculation time.
  • the adjustment module 16 analyzes the delay rate or the packet loss rate between the nodes of the optimal path to determine the node status.
  • the adjustment module 16 also adjusts the path weight of the node according to the node state, and updates the relevant path parameter and the optimal path according to the adjusted path weight.
  • the adjustment module 16 makes a corresponding adjustment when calculating the optimal path and the path selection according to the change parameter when the optimal path changes.
  • the parameter change further includes an error code
  • the control server 10 presets an adjustment threshold based on the error code.
  • the control server 10 scans the parameter changes under the corresponding path according to the path code, when When the error code found by the scan is greater than or equal to the adjustment threshold, the control server 10 adjusts the path parameter of the corresponding path node.
  • the control server 10 adjusts the weight of the node that has the error code on the corresponding path. For example, when the weight is zero, the node stops using the node, and when the weight is 1, the node is represented. Normal use.
  • the control server 10 adjusts the optimal path, in the probe data meter, the delay rate or the packet loss rate between the two network access terminals 20 in the optimal path may be spiked, and the control server 10 is calculating the most.
  • you have a good path you don't know whether the spike phenomenon happens by chance, that is, the peak we are talking about.
  • the control server 10 needs to log the history to judge.
  • the control server 10 can calculate the optimal path by using the average time value calculated by the cluster, and the control server 10 can avoid the influence of the spike when calculating the optimal path.
  • the control server 10 periodically requests information of the optimal path from the interface server.
  • the control server 10 finds that one of the optimal paths of a certain code has an error code. If the proportion of the error code reaches or exceeds the preset threshold value set by the control server 10, the control server 10 requests the interface server for the optimal path information for a longer time. Wherein, when the error code ratio continues to exceed the proportional threshold set by the control server 10, the access node is unavailable, and the weight of the access node is modified to be zero, that is, the control server 10 is optimally calculated. The path avoids the access node with zero weight.
  • the plurality of network access terminals 20-1 to 20-n constitute the application delivery network connected to the control server, wherein each of the network access terminals includes a receiving module 25, a label module 27, and a transmitting module 29;
  • the receiving module 25 receives the optimal path with path coding and path parameters from the response network request calculation sent by the control server 10.
  • the tag module 27 adds a path label to the optimal path according to the real path;
  • the transmitting module 29 uploads the optimal path of the added path label to the data processing terminal clusters 30-1 to 30-n, and the data processing terminal clusters 30-1 to 30-n determine the optimal based on the path parameters and the path label.
  • the parameters of the path and the real path change.
  • the receiving module 25 receives the update of the optimal path according to the parameter change.
  • each data processing terminal of the data processing terminal clusters 30-1 to 30-n includes a receiving module 35, an extracting module 36, an analyzing module 37, and an interface module 38.
  • the receiving module 35 receives the path with the response network access request sent from the control server 10
  • the path is encoded with the optimal path of the path parameters.
  • the extracting module 36 obtains the path label generated on the connected path and adds the path label on the optimal path according to the real path.
  • the analysis module 37 determines a parameter change of the optimal path and the real path based on the path parameter and the path label, and the parameter change is used to update the optimal path.
  • the interface module 38 is configured to transmit the parameter change to be stored to the data storage server 40.
  • the process of extracting the client access real path by the data processing terminal clusters 30-1 to 30-n is as follows:
  • the terminal 60 is sent to the plurality of nodes of the optimal path of the network side of the application delivery network 20 via the control server 10. Due to network conditions, node status, etc., the actual real path of the customer in the application delivery network is not necessarily the optimal path, and the real path changes according to the link and node conditions.
  • control server 10 In order for the network path optimization system to truly reflect the real link condition of each optimal path to obtain real access path information, the control server 10 needs to allocate a path code (pathID) for each optimal path to determine path parameters, such as an optimal path. Calculate the time (pathTime).
  • pathID path code
  • pathTime time
  • the link information format sent by the control server 10 to the network access end includes a path code (pathID) and a calculation time (pathTime).
  • the data processing terminal clusters 30-1 to 30-n determine the change of the path by coding when extracting the real path, and the same encoded path is the real path of the current access.
  • the network access terminal adds a path label (Session ID) to the link information according to the change between the real path and the optimal path, so that the link information format becomes three parts, specifically the obtained path code (pathID). , calculation time (pathTime) and label (Session ID).
  • the access network of the access extracts the changes that occur on the path node and establishes a history log.
  • the control server finds that the optimal path between the client terminal and the access source station changes frequently according to the historical log.
  • the delay rate and packet loss rate of the detection result at a certain moment are very high.
  • Phenomenon the analysis of the historical log is an accidental phenomenon. You can continue to use the existing link path without adjusting the optimal path. Therefore, using the historical log as a reference can avoid frequent path switching due to accidental phenomena.
  • a certain network end node often disconnects. According to the statistics of the historical log, the network access node often has a broken link, and the control server performs path selection. When modifying the weight of the network end node to avoid this node, select other network access nodes.
  • the control server 10 detects information such as delay rate and packet loss rate between each of the two network access nodes and the access source station, and calculates an optimal path according to the data.
  • the optimal path information is sent to the application delivery network 20, and is uploaded to the h data processing terminal clusters 30-1 to 30-n, and the information such as the delay rate, the packet loss rate, and the error code detected by the server 10 is uploaded.
  • the technical solution adds path coding (pathID, unique identifier of each optimal path) and calculation of the optimal path after the optimal path (BestPath). Time (pathTime, the time stamp of the optimal path is calculated each time).
  • pathID unique identifier of each optimal path
  • BestPath the optimal path after the optimal path
  • BestPath rtt, lost, weight, pathID, timeID
  • BestPath indicates the optimal path calculated by the control server 10
  • Rtt the average delay of the optimal path
  • PathID The path code of this path. The identifiers of the same path are the same.
  • timeID the time when this optimal path is calculated
  • the access logs generated by each incoming node of the application delivery network are also uploaded to the data processing terminal clusters 30-1 to 30-n. Due to network and node reasons, the real path of the client access and the control server 10 may be different. For example, if one node in the optimal path suddenly fails, the client access will skip this node, so the node Path encoding, calculation time, and label (pathID/pathTime/sessionID) are appended to each access log.
  • the original access log is accessContent, now as follows: accessContent pathID/pathTime/sessionID,
  • the path coding and calculation time are sent by the intelligent control server 10 to the application delivery network 20.
  • the tag is generated when the client accesses the network end node, and the path coding, calculation time, and label setting are convenient for searching.
  • the data processing terminal clusters 30-1 to 30-n calculate path parameters and history logs of the optimal path, and send calculation results of information such as error codes, average delays, and packet loss rates of each path to the data storage server 40. storage.
  • the interface server 50 will actively send the calculated data to the control server 10 at the same time, and will also listen to the request of the control server 10. When the control server 10 calculates the optimal path according to the calculated data, the corresponding adjustment is made with reference to the calculated data.
  • the network path optimization method provides an optimal path in response to the user request, adds a path label according to the real path of the network access terminal, and establishes a history log of the path label, and calculates an average delay rate and a packet loss rate between the nodes. And the result of the parameter change such as the error code, the optimal path is updated based on the parameter change, so as to reduce the switching frequency of the link path, and the network link is more rapid and stable.
  • Step 101 Calculate and send an optimal path with path coding and path parameters in response to the network access request, and the control server 10 calculates an optimal path with path coding and path parameters corresponding to the user's network access request, and The optimal path is sent to the network terminal of the application delivery network 20 that is connected to the user terminal and simultaneously sent to the data processing terminal clusters 30-1 to 30-n;
  • Step 102 Add a path label to the optimal path according to the real path, and add the path label to the optimal path according to the real path.
  • Step 103 Determine a parameter change between the optimal path and the real path based on the path parameter and the path label, and the data processing terminal clusters 30-1 to 30-n determine the optimal path based on the path parameter and the path label. Parameter changes between the real path and the real path;
  • Step 104 Update the optimal path according to the parameter change, and the control server 10 updates the optimal path according to the parameter change.
  • the optimal path includes a plurality of nodes, and the path parameter is a path weight of the node and an optimal path calculation time.
  • the path weight of the node is adjusted according to the state of the node.
  • the network path optimization method further includes storing the parameter change and the adjusted optimal path and path parameters to a data storage server.
  • the parameter change includes an error code
  • the updating the optimal path according to the parameter change includes the following steps:
  • the preset is based on an adjustment threshold of the error code
  • the path parameter of the corresponding path is adjusted; when the scanned error code continues to be greater than or equal to the adjustment threshold, the weight of the node with the error code on the corresponding path is adjusted.
  • a processing flow of the data processing terminal is implemented to implement the network path optimization method.
  • the network path optimization method of the data processing terminal includes the following steps:
  • Step 201 Calculate and send an optimal path with path coding and path parameters in response to the network access request;
  • Step 202 Acquire a parameter change of an optimal path and a real path based on the path parameter and the path label analysis, where the path label is added to the optimal path according to the real path;
  • Step 203 Update the parameter change and store the parameter change.
  • the steps according to the update parameter change further include:
  • the path weight of the node is adjusted according to the state of the node.
  • FIG. 6 is a flowchart showing a method for implementing the network path optimization method and each incoming network end.
  • Step 301 Receive an optimal path with a path code and a path parameter calculated in response to the incoming network request, the optimal path from the control server 10;
  • Step 302 Add a path label to the optimal path according to the real path.
  • Step 303 Upload the optimal path of the added path label to the data processing terminal cluster, where the data processing terminal cluster determines parameter changes of the optimal path and the real path based on the path parameter and the path label.
  • Step 304 Receive an optimal path updated according to the parameter change, and the optimal path is sent from the control server 10.
  • FIG. 7 illustrates a method for implementing the network path optimization method, and each data processing terminal processing flow.
  • Step 401 Receive an optimal path with a path code and a path parameter calculated in response to the incoming network request, the optimal path from the control server 10;
  • Step 402 Acquire a path label on the optimal path according to the real path, and obtain the path label data from the corresponding network access end.
  • Step 403 Determine, according to the path parameter and the path label, a parameter change of the optimal path and the real path, where the parameter change is used to update the optimal path;
  • Step 404 Send a parameter change to be stored, and the parameter change is stored in the data storage server 40.
  • the network path optimization method and system of the embodiment provided by the embodiment of the present application are provided in response to a user request.
  • the optimal path the network end adds tags according to the real path, such as the average delay rate and packet loss rate or error code between the nodes, and establishes a history log according to the path label, calculates a parameter change according to the history log, and updates based on the parameter change.
  • the optimal path thereby reducing the switching frequency of the link path, and making the network link more stable; at the same time, the network path optimization method and the control server of the system obtain the parameter change of the encoded optimal path, and the control server according to the data
  • the parameter change calculation result stored in the storage server 40 such as the error rate and the like, adjusts the update path parameter and the optimal path to provide a dynamic path that adapts to the current network environment, or adjusts the weight of the optimal path node to implement Update and adjust the optimal path.
  • FIG. 11 is a schematic diagram showing the hardware structure of an electronic device 600 according to the network path optimization method provided by the embodiment of the present application. As shown in FIG. 11, the electronic device 600 includes:
  • One or more processors 610, a memory 620, and a communication component 650 are illustrated by one processor 610 in FIG.
  • the memory 620 stores instructions executable by the at least one processor 610, the instructions being executed by the at least one processor, establishing a data channel through the communication component 650 to enable the at least one processor to perform the network path optimization method .
  • the processor 610, the memory 620, and the communication component 650 may be connected by a bus or other means, as exemplified by a bus connection in FIG.
  • the memory 620 is a non-volatile computer readable storage medium, and can be used for storing a non-volatile software program, a non-volatile computer executable program, and a module, such as a program corresponding to the network path optimization method in the embodiment of the present application.
  • An instruction/module for example, the distribution module 12, the acquisition module 14 and the adjustment module 16, shown in Fig. 11, the reception module 25, the label module 27, and the transmission module 29 shown in Fig. 12).
  • the processor 610 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 620, that is, implementing the network path optimization method in the foregoing method embodiments.
  • the memory 620 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the robot electronic device, and the like.
  • memory 620 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.
  • the memory 620 can optionally include relative to
  • the processor 610 is remotely located with a memory that can be connected to the robotic interactive electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the one or more modules are stored in the memory 620, and when executed by the one or more processors 610, perform a network path optimization method in any of the above method embodiments, for example, performing the above described FIG.
  • steps 101 to 104 of the method the method steps 201 to 203 in FIG. 5 described above are performed, and the method steps 301 to 304 in FIG. 6 described above are performed to implement the allocation module 12 and the acquisition module in FIG. 14.
  • Adjustment module 16 the functions of receiving module 25, tag module 27, transfer module 29, etc. in FIG.
  • Embodiments of the present application provide a non-transitory computer readable storage medium storing computer-executable instructions that are executed by one or more processors, for example, to perform the above
  • the method steps 101 to 104 in FIG. 4 described above, the method steps 201 to 203 in FIG. 5 described above are performed, and the method steps 301 to 304 in FIG. 6 described above are performed to implement the allocation module in FIG. 12.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

一种网络路径优化方法，包括以下步骤：响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径，其中，所述最优路径建立在多个节点之间；根据真实路径，在该最优路径上添加路径标签；基于该路径参数以及该路径标签确定该最优路径和真实路径之间的参数变化；根据该参数变化更新该最优路径以及所述路径参数。

Description

一种网络路径优化方法、系统、控制服务端以及入网端 技术领域
本申请涉及应用交付网络(Application delivery network,ADN)领域，具体涉及一种基于数据分析的网络路径优化方法、系统、控制服务端以及入网端。
背景技术
随着网络传输硬件处理能力的提升以及移动终端的普及，网络负载越来越大，用户对网络传输性能和安全问题的要求也越来越多高。
应用交付网络(Application Delivery Network，简称ADN)，利用相应的网络优化/加速设备，通过软件和硬件设备及网络优化来确保用户的业务应用能够快速、安全、可靠地交付给内部用户和外部服务群。
在传统应用交付网络的网络优化中，最优路径选择是根据实时探测的网络延迟和丢包率等信息，通过最短路径算法进行路径选择。探测数据每分钟会根据当前探测数据，判断当前路径网络状况，决定是否进行路径的切换，没有参考历史数据。
但是，由于网络环境比较复杂，探测数据存在偶然性，计算的最优路径在链接后，很可能存在不稳定的状况。访问所经过的路径是根据最优路径算法所选择的路径，由于网络状况复杂，最优路径中两个相邻设备之间的网络状况，可能存在故障出现无法链接等状况或者会产生链接错误等信息，因此，现有技术的最优路径无法准确的反应出真实的链路路径，不能准确的反映出历史路径状况。
并且，对于一些专有客户，需要凭借经验进行手动路径选择，在选择时没有链路历史数据作为依据，可靠性和效率都不高。
因此，现有技术的应用交付网络的网络优化技术还有待于改进。
申请内容
本申请提供一种网络路径优化方法、系统、控制服务端以及入网端，该网络路径优化方法以及系统响应用户请求提供最优路径，并根据入网端真实路径 识别出与最优路径的参数变化，添加可修改的标签，比如节点状况，基于该参数变化和标签动态更新该最优路径，从而减少链路路径的切换频率，使网络链接更加稳定。
第一方面，本申请实施例提供了一种网络路径优化方法，包括以下步骤：
响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
根据真实路径，在该最优路径上添加路径标签；
基于该路径参数以及该路径标签确定该最优路径和真实路径之间的参数变化；
根据该参数变化更新该最优路径以及路径参数。
第二方面，从控制服务端来看，本申请实施例提供了一种网络路径优化方法，包括如下步骤：
响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
获取基于该路径参数以及路径标签分析而得的最优路径和真实路径的参数变化，该路径标签为根据该真实路径而添加至该最优路径；
根据该参数变化更新该最优路径以及路径参数。
第三方面，从入网端来看，本申请实施例提供了一种网络路径优化方法，包括如下步骤：
接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
根据真实路径，在该最优路径上添加路径标签；
将添加路径标签的该最优路径上传至数据处理终端集群，该数据处理终端集群基于该路径参数以及路径标签确定该最优路径和真实路径的参数变化；
接收根据该参数变化更新该最优路径以及路径参数。
第四方面，从数据处理终端来看，本申请实施例提供了一种网络路径优化方法，包括如下步骤：
接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
获取根据真实路径以及该最优路径上增添的路径标签；
基于该路径参数以及路径标签确定最优路径和真实路径的参数变化，该参数变化用于更新该最优路径；
发送待存储的该参数变化。
第五方面，本申请实施例还提供了一种网络路径优化系统，包括控制服务 端、若干入网端以及数据处理终端集群，该若干入网端组网，该若干入网端与控制服务端和数据处理终端集群通信连接，该控制服务端与该数据处理终端集群通信连接；
其中，该控制服务端用于响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
该入网端用于根据真实路径，在该最优路径上添加路径标签；
该数据处理终端集群用于基于该路径参数以及该路径标签确定该最优路径和真实路径之间的参数变化；
该控制服务端还用于根据该参数变化更新该最优路径以及路径参数。
第六方面，从单独处理终端阐述，本申请实施例提供了一种控制服务端，包括分配模块、获取模块以及调整模块：
该分配模块用于响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
该获取模块用于获取基于该路径参数以及路径标签分析而得的最优路径和真实路径的参数变化，该路径标签为根据该真实路径而添加至该最优路径；
该调整模块用于根据该参数变化更新该最优路径以及该路径参数。
第七方面，从单独处理终端阐述，本申请实施例提供了一种入网端，包括接收模块、标签模块以及传送模块；
该接收模块用于接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
该标签模块用于根据真实路径，在该最优路径上添加路径标签；
该传送模块用于将添加路径标签的该最优路径上传至数据处理终端集群，该数据处理终端集群基于该路径参数以及路径标签确定该最优路径和真实路径的参数变化；
该接收模块还用于接收根据该参数变化更新的最优路径以及路径参数。
第八方面，从单独处理终端阐述，本申请实施例提供了一种数据处理终端，包括接收模块、提取模块、分析模块以及接口模块，
该接收模块用于接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
该提取模块用于获取根据真实路径而增添在该最优路径上的路径标签；
该分析模块用于基于该路径参数以及路径标签确定最优路径和真实路径的参数变化，该参数变化用于更新该最优路径；
该接口模块用于传送待存储的该参数变化。
第九方面，本申请实施例还提供了一种电子设备，包括：
至少一个处理器；以及，
与该至少一个处理器通信连接的存储器以及通信组件；其中，
该存储器存储有可被该至少一个处理器执行的指令，该指令被该至少一个处理器执行时，通过通信组件建立数据通道，以使该至少一个处理器能够执行如上所述的方法。
第十方面，本申请实施例还提供了一种非易失性计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使计算机执行如上所述的方法。
第十一方面，本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行如上所述的方法。
本申请的有益效果在于，本申请实施例提供网络路径优化方法、系统、控制服务端以及入网端，该网络路径优化方法以及系统响应用户请求提供最优路径，并根据入网端真实路径添加标签，并根据标签建立历史日志，基于历史日志识别节点之间的平均延迟率和丢包率或者错误码等参数和状况，用于更新该最优路径，减少链路路径的切换频率，使网络链接更加稳定；同时，该网络路径优化方法以及系统的控制服务端获取已编码的最优路径的变化参数，该控制服务端根据该变化参数以及标签，比如错误率等信息，调整最优路径的路径参数，比如节点的路径权重以及计算最优路径的时间，以调整最优路径选择，或者调整最优路径上两个节点之间的权重，以实现最优路径动态调整。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是本申请实施例提供的网络路径优化系统的系统架构图；
图2是本申请实施例提供的网络路径优化系统的最优路径示意图；
图3是本申请实施例提供的网络路径优化系统的真实路径示意图；
图4是本申请实施例提供的网络路径优化方法的主要流程图；
图5是本申请实施例提供的网络路径优化方法的控制服务端流程图；
图6是本申请实施例提供的网络路径优化方法的入网端流程图；
图7是本申请实施例提供的网络路径优化方法的数据处理终端流程图；
图8是本申请实施例提供的网络路径优化系统的控制服务端模块图；
图9是本申请实施例提供的网络路径优化系统的入网端模块图；
图10是本申请实施例提供的网络路径优化系统的数据处理终端模块图；以及
图11是本申请实施例提供的为实现网络路径优化方法的硬件框架图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。
本申请实施例提供的网络路径优化方法和系统响应用户请求提供动态调整的最优路径，在入网端接入时根据真实路径和最优路径之间的参数变化添加标签，并建立历史日志，以基于参数变化和标签动态更新该最优路径，从而减少链路路径的切换频率，使网络链接更加稳定。
如图1所示，该网络路径优化方法和系统应用于应用交付网络(Application Delivery Network，简称ADN)，建立网路优化服务器集群，包括入网端组成的应用交付网络20、控制服务器10、完成大数据分析的数据处理终端集群30、数据存储服务器40和接口服务器50。该网络路径优化系统对计算的最优路径进行编码，添加路径参数以及增设事件标签，基于分工的服务器设备，以控制服务器10为处理中心，加速访问路径链路的建立，减少链路路径的切换频率，使网络链接更加稳定。
该应用交付网络20由若干入网端20-1、入网端20-2、入网端20-3…入网端20-n组成。该等入网端为应用交付网络20的入网点，入网点位于网络的边 缘外侧，是访问网络内部的进入点，互联网服务提供商(Internet Service Provider，ISP)提供的服务通过入网端进入，该服务包括Internet接入，广域连接或者电话服务(PSTN)。该入网端(POP端)提供通往服务和站点的链路。对于互联网服务提供商来说，入网端是一个将互联网从一个地方接到其他地方的入网点。一般互联网服务提供商(ISP)或在线服务提供商在互联网上有一个或者若干个入网点。互联网服务提供商(ISP)所拥有的入网点数量可作为衡量规模和增长速度的标准。入网端可以是独立服务器节点或者是安装在电信运营商的租用空间，入网端一般包括路由器、以及服务器等。
该数据处理终端集群30以大数据处理方式接收最优路径以及应用交付网络20对最优路径增加的路径标签，以提取真实路径的信息和行成该最优路径的更新参考数据。
实施例1
请进一步参考图1至图3，本实施例的网络路径优化系统，包括控制服务端10、若干入网端20-1至20-n、数据存储服务器40、接口服务器50以及数据处理终端集群30-1至30-n。该若干入网端20-1至20-n组网成为应用交付网络。该若干入网端20-1至20-n与控制服务端连接，该若干入网端20-1至20-n和数据处理终端集群30-1至30-n通信连接。该控制服务端10与该数据处理终端集群30-1至30-n通信连接。该数据处理终端集群30-1至30-n产生的参数变化数据发送至数据存储服务器40进行存储，该控制服务端10定期向接口服务器50请求最优路径的路径参数和参数变化。其中，入网端20-1至20-n增加的路径标签以及生产的历史日志存储在该数据处理终端集群30-1至30-n中，该数据存储服务器40中存储计算而得的参数变化结果，根据该路径参数和参数变化对该最优路径进行修改和调整。
当用户发出入网请求时，该控制服务端10响应入网请求，计算有路径编码并带有路径参数的最优路径，并将该最优路径信息发送给应用交付网络20中接收入网请求的入网端，比如入网端20-1，同时也发送给数据处理终端集群30-1至30-n。
该入网端20-1收到具有路径编码并带有路径参数的最优路径后，根据最优 路径建立链路，并依据真实路径的链路状况，在收到的最优路径上添加路径标签，比如节点之间的平均延迟率和丢包率或者错误码等。
该数据处理终端集群30-1至30-n基于该路径参数以及该路径标签确定该最优路径和真实路径之间的参数变化。
该数据处理终端集群30-1至30-n通信连接数据存储服务器40。该数据存储服务器40存储数据处理终端集群30-1至30-n的计算结果，比如参数变化。
该控制服务端10根据该参数变化和更新该最优路径，从而为用户请求提供稳定快速、与网络状况一致的连接链路。
请参考图8，该控制服务端包括分配模块12、获取模块14以及调整模块16。
该最优路径为从用户终端60开始经过应用交付网络20的若干接入端节点到访问源站70结束，包括多台节点。本实施例中，该路径参数为节点的路径权重以及最优路径计算时间，其中，该数据处理终端集群还用于分析该最优路径的节点之间的延迟率或者丢包率等相关参数状态以及参数变化，确定节点状态。
在网络路径优化上，控制服务端的作用为：
计算有路径编码并带有路径参数的最优路径，并将该最优路径信息发送给应用交付网络20中接收入网请求的入网端，比如入网端20-1，同时也发送给数据处理终端集群30-1至30-n。
该获取模块14获取基于该路径参数以及路径标签分析而得的最优路径和真实路径的参数变化，该路径标签是根据该真实路径而添加至该最优路径上的。
该调整模块16根据该参数变化和更新该最优路径。
其中，该最优路径一般都会包括多台节点。本实施例中，该路径参数为节点的路径权重以及最优路径计算时间。
该调整模块16分析该最优路径的节点之间的延迟率或者丢包率，确定节点状态。
该调整模块16还根据节点状态调整节点的路径权重，以及根据调整的路径权重更新相关路径参数以及最优路径。
该调整模块16在最优路径有变化时，根据变化参数在计算最优路径和路径选择时做出对应的调整。
本实施例中，该参数变化还包括错误码，该控制服务端10预设基于错误码的调整阈值。该控制服务端10根据该路径编码扫描对应路径下的参数变化，当 扫描发现的错误码大于等于调整阈值时，该控制服务端10调整对应路径节点的路径参数。当扫描的错误码经判断发现持续大于等于调整阈值时，该控制服务端10调整对应路径上出现错误码的节点的权重，比如权重为零时表示该停止使用该节点，权重为1时表示节点正常使用。
该控制服务端10调整最优路径时，在探测数据计中，最优路径中的两个入网端20之间的延迟率或者丢包率会出现尖峰现象，此时控制服务端10在计算最优路径时不知道该尖峰现象是否偶然出现，即我们所说的尖峰。为了在计算最优路径时判断是否存在尖峰，控制服务端10需要历日志来加以判断。当是尖峰时，控制服务端10可以采用集群计算的平均时间值计算最优路径，控制服务端10在计算最优路径时可规避尖峰的影响。
或者，该控制服务端10定时向接口服务器请求最优路径的信息。当控制服务端10发现某一编码的最优路径中的一个入网端出现了错误码。如果出现错误码的比例达到或超过控制服务端10预先设定的比例阈值，控制服务端10会向接口服务器请求更长时间的最优路径信息。其中，在错误码比例持续超过控制服务端10设定的比例阈值时，则此接入端节点为不可使用，修改该接入端节点的权重为零，亦即控制服务端10在计算最优路径时规避权重为零的接入端节点。
请参考图9，该若干入网端20-1至20-n组成该与控制服务端连接的应用交付网络，其中每一入网端包括接收模块25、标签模块27以及传送模块29；
在网络路径优化上，每一入网端20-1至20-n的作用为：
该接收模块25接收来自控制服务端10发送的响应入网请求计算的具有路径编码并带有路径参数的最优路径。
该标签模块27根据真实路径，在该最优路径上添加路径标签；
该传送模块29将添加路径标签的该最优路径上传至数据处理终端集群30-1至30-n，该数据处理终端集群30-1至30-n基于该路径参数以及路径标签确定该最优路径和真实路径的参数变化。
该接收模块25接收根据该参数变化更新该最优路径。
请参考图10，数据处理终端集群30-1至30-n的每一数据处理终端包括接收模块35、提取模块36、分析模块37以及接口模块38。
在网络路径优化上，每一数据处理终端的作用为：
该接收模块35接收来自控制服务端10发送的响应入网请求计算的具有路 径编码并带有路径参数的最优路径。
该提取模块36获取所连接入网端产生的根据真实路径，增添在该最优路径上的路径标签。
该分析模块37基于该路径参数以及路径标签确定最优路径和真实路径的参数变化，该参数变化用于更新该最优路径。
该接口模块38用于传送待存储的该参数变化至该数据存储服务器40。
请一并参考图2和图3，该数据处理终端集群30-1至30-n提取客户访问真实路径的过程介绍如下：
如图2所示，客户通过终端60在访问源站70经过应用交付网络20时，会经过控制服务端10下发给应用交付网络20的入网端的最优路径的多台节点。由于网络状况、节点状态等原因客户在应用交付网络中的实际真实路径并非必然是最优路径，依据链路和节点状况该真实路径有所改变。
为了网络路径优化系统能够真实反映每一最优路径的真实链路情况获取真实访问路径信息，控制服务端10需要为每一最优路径分配路径编码(pathID)确定路径参数，比如最优路径的计算时间(pathTime)。
本实施例中，该控制服务端10下发给入网端的链路信息格式，包括路径编码(pathID)、计算时间(pathTime)。数据处理终端集群30-1至30-n在提取真实路径时以编码判断路径的变化，相同编码的路径即是此次访问的真实路径。具体接入的入网端根据真实路径与最优路径之间的变化在链路信息上增加路径标签(Session ID)，使得该链路信息格式变为三部分，具体为获取的路径编码(pathID)、计算时间(pathTime)以及标签(Session ID)。接入的入网端提取路径节点发生的变化，建立历史日志。
应用举例：某公司应用交付网络中，控制服务端根据历史日志发现客户终端和访问源站之间的最优路径发生频繁变化，在某一时刻的探测结果出现延迟率和丢包率非常高的现象，分析历史日志发现属于偶然现象，可以不调整该最优路径继续采用现存的链路路径，因此以历史日志作为参考可避免由于偶然现象导致的频繁路径切换。在另一优化场景中，最优路径链接后，某一入网端节点经常出现断开连接的现象，根据历史日志的统计，该入网端节点经常出现断开链接的情况，控制服务器在进行路径选择时，修改该入网端节点的权重以避开此节点，选择其他入网端节点。
以下是该网络路径优化系统的工作过程：控制服务端10探测每两个入网端节点和访问源站之间的延迟率、丢包率等信息，并根据数据计算最优路径。将最优路径信息下发到应用交付网络20中，同时上传到h数据处理终端集群30-1至30-n中，另外控制服务端10探测的延迟率、丢包率、错误码等信息上传至数据处理终端集群30-1至30-n。为了在系统的数据分配传输和分析能针对特定的客户端访问路径，本技术方案在最优路径(BestPath)后加入路径编码(pathID，每条最优路径的唯一标识)和最优路径的计算时间(pathTime，每次计算最优路径的时间标识)。格式如下：
BestPath：rtt，lost，weight，pathID，timeID
BestPath：表示控制服务端10计算的最优路径；
rtt：最优路径的平均延迟；
lost：最优路径的平均丢包率；
PathID：此条路径的路径编码，相同路径的标识是相同的；
timeID：计算此条最优路径时的时间；
应用交付网络每个入网端节点产生的访问日志同样会上传至数据处理终端集群30-1至30-n。由于网络和节点原因，客户访问的真实路径和控制服务端10可能会有一些不同，比如最优路径中的一台节点突然不通，那么将会客户访问将会跳过此节点，因此在节点的每一条访问日志后面追加路径编码、计算时间以及标签(pathID/pathTime/sessionID)。假设原来每条访问日志是accessContent，现在如下：accessContent pathID/pathTime/sessionID，
路径编码、计算时间由智能控制服务端10下发到应用交付网络20中的，标签是客户访问入网端节点时有入网端节点生成的，该路径编码、计算时间以及标签的设置是为了便于找出客户访问走的真实访问路径。
该数据处理终端集群30-1至30-n计算最优路径的路径参数和历史日志，将每条路径的错误码、平均延迟、丢包率等信息的计算结果发送到数据存储服务器40中进行存储。接口服务器50会主动定时将计算数据发送到控制服务端10，同时也会监听控制服务端10的请求。控制服务端10根据计算数据在计算最优路径时，会参考计算数据做出相应调整。
实施例2
请参考图4，该网络路径优化方法响应用户请求提供最优路径，并根据入网端真实路径添加路径标签，并建立路径标签的历史日志，并计算出节点之间的平均延迟率、丢包率和错误码等参数变化结果，基于参数变化更新该最优路径，以减少链路路径的切换频率，使网络链接更加快速稳定。
本实施例的网络路径优化方法，包括以下步骤：
步骤101：响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径，该控制服务端10相应用户的入网请求，计算具有路径编码并带有路径参数的最优路径，并将该最优路径发送给应用交付网络20中与用户终端对接的入网端同时发送给数据处理终端集群30-1至30-n；
步骤102：根据真实路径，在该最优路径上添加路径标签，该与用户终端对接的入网端根据真实路径，在该最优路径上添加路径标签；
步骤103：基于该路径参数以及该路径标签确定该最优路径和真实路径之间的参数变化，该数据处理终端集群30-1至30-n基于该路径参数以及该路径标签确定该最优路径和真实路径之间的参数变化；
步骤104：根据该参数变化更新该最优路径，该控制服务端10根据该参数变化更新该最优路径。
该最优路径包括多台节点，该路径参数为节点的路径权重以及最优路径计算时间。
该基于该路径参数以及该路径标签确定该最优路径和真实路径之间的参数变化包括步骤：
分析该最优路径的节点之间的延迟率或者丢包率，确定节点状态；
根据节点状态调整节点的路径权重。
该网络路径优化方法还包括将该参数变化以及调整的最优路径以及路径参数存储至数据存储服务器。
其中，该参数变化包括错误码，根据参数变化更新该最优路径包括步骤：
预设基于错误码的调整阈值；
根据该路径编码扫描对应路径下的参数变化；
当扫描的错误码大于等于调整阈值时，调整对应路径的路径参数；当扫描的错误码持续大于等于调整阈值时，调整对应路径上出现错误码的节点的权重。
从控制服务端介绍该网络路径优化方法：
请参考图5，所示为实现该网络路径优化方法，该数据处理终端的处理流程。
该数据处理终端的网络路径优化方法，包括如下步骤：
步骤201：响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
步骤202：获取基于该路径参数以及路径标签分析而得的最优路径和真实路径的参数变化，该路径标签根据该真实路径添加至该最优路径上；
步骤203：更新参数变化以及存储该参数变化。
根据该更新参数变化的步骤还包括：
分析计算该最优路径的节点的延迟率或者丢包率，确定节点状态；
根据节点状态调整节点的路径权重。
请参考图6，所示为实现该网络路径优化方法，每一入网端的处理流程。
本实施例的每一入网端的网络路径优化方法，包括如下步骤：
步骤301：接收响应入网请求计算的具有路径编码并带有路径参数的最优路径，该最优路径来自该控制服务端10；
步骤302：根据真实路径，在该最优路径上添加路径标签；
步骤303：将添加路径标签的该最优路径上传至数据处理终端集群，该数据处理终端集群基于该路径参数以及路径标签确定该最优路径和真实路径的参数变化；
步骤304：接收根据该参数变化更新的最优路径，该最优路径发送自该控制服务端10。
请参考图7，所示为实现该网络路径优化方法，每一数据处理终端处理流程。
本实施例的每一数据处理终端的网络路径优化方法，包括如下步骤：
步骤401：接收响应入网请求计算的具有路径编码并带有路径参数的最优路径，该最优路径来自该控制服务端10；
步骤402：获取根据真实路径，增添在该最优路径上的路径标签，从对应的入网端获取该路径标签数据；
步骤403：基于该路径参数以及路径标签确定最优路径和真实路径的参数变化，该参数变化用于更新该最优路径；
步骤404：发送待存储的参数变化，该参数变化存储在数据存储服务器40。
本申请实施例提供的网络路径优化方法和系统的入网端响应用户请求提供 最优路径，该入网端根据真实路径添加标签，比如节点之间的平均延迟率和丢包率或者错误码等，并根据路径标签建立历史日志，根据历史日志计算出参数变化，基于参数变化更新该最优路径，从而减少链路路径的切换频率，使网络链接更加稳定；同时，该网络路径优化方法以及系统的控制服务端获取已编码的最优路径的参数变化，该控制服务端根据数据存储服务器40中存储的参数变化计算结果，比如错误率等信息，调整更新路径参数以及最优路径，以提供动态的适应当前网络环境的最优路径，或者调整最优路径节点的权重，以实现最优路径的更新和调整。
实施例6
图11是本申请实施例提供的网络路径优化方法的电子设备600的硬件结构示意图，如图11所示，该电子设备600包括：
一个或多个处理器610、存储器620以及通信组件650，图11中以一个处理器610为例。该存储器620存储有可被该至少一个处理器610执行的指令，该指令被该至少一个处理器执行时，通过通信组件650建立数据通道，以使该至少一个处理器能够执行该网络路径优化方法。
处理器610、存储器620以及通信组件650可以通过总线或者其他方式连接，图11中以通过总线连接为例。
存储器620作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的网络路径优化方法对应的程序指令/模块(例如，附图11所示的分配模块12、获取模块14和调整模块16，附图12所示的接收模块25、标签模块27和传送模块29)。处理器610通过运行存储在存储器620中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例中的网络路径优化方法。
存储器620可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据机器人电子设备的使用所创建的数据等。此外，存储器620可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器620可选包括相对于处 理器610远程设置的存储器，这些远程存储器可以通过网络连接至机器人交互电子设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器620中，当被所述一个或者多个处理器610执行时，执行上述任意方法实施例中的网络路径优化方法，例如，执行以上描述的图4中的方法步骤101至步骤104，执行以上描述的图5中的方法步骤201至步骤203以及执行以上描述的图6中的方法步骤301至步骤304，实现图8中的分配模块12、获取模块14、调整模块16，图9中的接收模块25、标签模块27、传送模块29等的功能。
上述产品可执行本申请实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本申请实施例所提供的方法。
本申请实施例提供了一种非易失性计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行，例如，执行以上描述的图4中的方法步骤101至步骤104，执行以上描述的图5中的方法步骤201至步骤203以及执行以上描述的图6中的方法步骤301至步骤304，实现图8中的分配模块12、获取模块14、调整模块16，图9中的接收模块25、标签模块27、传送模块29等的功能。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施方式的描述，本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；在本申请的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本申请的不同方面的许多其它变化，为了简明，它们没有在细节中提供；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (19)

  1. 一种网络路径优化方法，其特征在于，包括以下步骤：
    响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
    根据真实路径，在所述最优路径上添加路径标签；
    基于所述路径参数以及所述路径标签确定所述最优路径和真实路径之间的参数变化；
    根据所述参数变化更新所述最优路径以及所述路径参数。
  2. 根据权利要求1所述的方法，其特征在于，所述最优路径建立在多个节点之间，所述路径参数为节点的路径权重以及最优路径计算时间，所述基于所述路径参数以及所述路径标签确定所述最优路径和真实路径之间的参数变化包括步骤：
    分析所述最优路径的节点之间的延迟率或者丢包率，确定节点状态；
    根据所述节点状态调整节点的路径权重。
  3. 根据权利要求2所述的方法，其特征在于，还包括将所述更新的最优路径以及更新的路径参数存储至数据存储服务器。
  4. 根据权利要求1-3任意一项所述的方法，其特征在于，所述参数变化包括错误码，所述根据所述参数变化更新所述最优路径以及所述路径参数的步骤还包括：
    预设基于错误码的调整阈值；
    根据所述路径编码扫描对应最优路径下的参数变化；
    当扫描的错误码大于等于调整阈值时，调整对应路径的路径参数；当扫描的错误码持续大于等于调整阈值时，调整对应路径上出现错误码的节点的权重。
  5. 一种网络路径优化方法，其特征在于，包括如下步骤：
    响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
    获取基于所述路径参数以及路径标签分析而得的最优路径和真实路径的参数变化，所述路径标签为根据所述真实路径变化而添加至所述最优路径上；
    根据所述参数变化更新所述最优路径以及所述路径参数。
  6. 根据权利要求5所述的方法，其特征在于，所述最优路径建立在多个节点之间，所述路径参数为节点的路径权重以及最优路径计算时间，所述根据所述参数变化更新所述最优路径以及所述路径参数的步骤还包括：
    分析所述最优路径的节点之间的路径参数以及参数变化，确定节点状态，其中，所述参数变化包括延迟率以及丢包率；
    根据所述节点状态调整节点的路径权重。
  7. 一种网络路径优化方法，其特征在于，包括如下步骤：
    接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
    根据真实路径，在所述最优路径上添加路径标签；
    将添加路径标签的所述最优路径上传至数据处理终端集群，所述数据处理终端集群基于所述路径参数以及路径标签确定所述最优路径和真实路径的参数变化；
    接收根据所述参数变化更新的最优路径以及路径参数。
  8. 一种网络路径优化方法，其特征在于，包括如下步骤：
    接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
    获取根据真实路径在所述最优路径上增添的路径标签；
    基于所述路径参数以及路径标签确定最优路径和真实路径的参数变化，所述参数变化用于更新所述路径参数以及最优路径；
    发送待存储的所述参数变化。
  9. 一种网络路径优化系统，其特征在于，包括控制服务端、若干入网端以及数据处理终端集群，所述若干入网端组网，所述若干入网端与控制服务端和数据处理终端集群通信连接，所述控制服务端与所述数据处理终端集群通信连接；
    其中，所述控制服务端用于响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
    所述入网端用于根据真实路径，在所述最优路径上添加路径标签；
    所述数据处理终端集群用于基于所述路径参数以及所述路径标签确定所述最优路径和真实路径之间的参数变化；
    所述控制服务端还用于根据所述参数变化更新所述最优路径以及所述路径参数。
  10. 根据权利要求9所述的系统，其特征在于，所述最优路径包括多台节点，所述路径参数为节点的路径权重以及最优路径计算时间，其中，所述数据处理终端集群还用于分析所述最优路径的节点之间的延迟率或者丢包率，确定节点 状态；
    所述控制服务端还用于根据所述节点状态调整节点的路径权重，以及根据调整的路径权重更新所述最优路径。
  11. 根据权利要求9所述的系统，其特征在于，还包括与所述数据处理终端集群通信连接的数据存储服务器，所述数据存储服务器存储所述参数变化以及更新的最优路径和路径参数。
  12. 根据权利要求9-11任意一项所述的系统，其特征在于，所述参数变化包括错误码，预设基于错误码的调整阈值；其中，所述控制服务端还用于根据所述路径编码扫描对应路径下的参数变化；当扫描的错误码大于等于调整阈值时，所述控制服务端用于调整对应路径的路径参数；当扫描的错误码持续大于等于调整阈值时，所述控制服务端用于调整对应路径上出现错误码的节点的权重。
  13. 一种控制服务端，其特征在于，包括分配模块、获取模块以及调整模块：
    所述分配模块用于响应入网请求，计算和发送具有路径编码并带有路径参数的最优路径；
    所述获取模块用于获取基于所述路径参数以及路径标签分析而得的最优路径和真实路径的参数变化，所述路径标签为根据所述真实路径而添加至所述最优路径；
    所述调整模块用于根据所述参数变化和更新所述最优路径。
  14. 根据权利要求13所述的控制服务端，其特征在于，所述最优路径包括多台节点，所述路径参数为节点的路径权重以及最优路径计算时间，所述调整模块还用于分析所述最优路径的节点之间的延迟率或者丢包率，确定节点状态；所述调整模块还用于根据节点状态调整节点的路径权重。
  15. 一种入网端，其特征在于，包括接收模块、标签模块以及传送模块；
    所述接收模块用于接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
    所述标签模块用于根据真实路径，在所述最优路径上添加路径标签；
    所述传送模块用于将添加路径标签的所述最优路径上传至数据处理终端集群，所述数据处理终端集群基于所述路径参数以及路径标签确定所述最优路径和真实路径的参数变化；
    所述接收模块还用于接收根据所述参数变化更新所述最优路径以及所述路径参数。
  16. 一种数据处理终端，其特征在于，包括接收模块、提取模块、分析模块以及接口模块，
    所述接收模块用于接收响应入网请求计算的具有路径编码并带有路径参数的最优路径；
    所述提取模块用于获取根据真实路径增添在所述最优路径上的路径标签；
    所述分析模块用于基于所述路径参数以及路径标签确定最优路径和真实路径的参数变化，所述参数变化用于更新所述最优路径；
    所述接口模块用于传送待存储的所述参数变化。
  17. 一种电子设备，其中，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器以及通信组件；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行时，通过通信组件建立数据通道，以使所述至少一个处理器能够执行权利要求1-8任一项所述的方法。
  18. 一种非易失性计算机可读存储介质，其中，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使计算机执行权利要求1-8任一项所述的方法。
  19. 一种计算机程序产品，其中，所述计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行权利要求1-8任一项所述的方法。
PCT/CN2017/106577 2017-10-17 2017-10-17 一种网络路径优化方法、系统、控制服务端以及入网端 WO2019075642A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201780002591.8A CN108064439B (zh) 2017-10-17 2017-10-17 一种网络路径优化方法、系统、控制服务端以及入网端
PCT/CN2017/106577 WO2019075642A1 (zh) 2017-10-17 2017-10-17 一种网络路径优化方法、系统、控制服务端以及入网端
US16/783,476 US11146482B2 (en) 2017-10-17 2020-02-06 Network path optimization method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/106577 WO2019075642A1 (zh) 2017-10-17 2017-10-17 一种网络路径优化方法、系统、控制服务端以及入网端

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/783,476 Continuation US11146482B2 (en) 2017-10-17 2020-02-06 Network path optimization method and system

Publications (1)

Publication Number Publication Date
WO2019075642A1 true WO2019075642A1 (zh) 2019-04-25

Family

ID=62142059

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/106577 WO2019075642A1 (zh) 2017-10-17 2017-10-17 一种网络路径优化方法、系统、控制服务端以及入网端

Country Status (3)

Country Link
US (1) US11146482B2 (zh)
CN (1) CN108064439B (zh)
WO (1) WO2019075642A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109067668B (zh) * 2018-09-19 2022-03-04 苏州瑞立思科技有限公司 基于智能均衡分配的全球网络加速链路构建方法
CN109745703B (zh) * 2018-12-29 2022-06-03 网易（杭州）网络有限公司 自适应加速方法、装置及存储介质
CN112422425B (zh) * 2020-10-10 2023-01-10 锐捷网络股份有限公司 一种线路确定方法、装置、网关设备和存储介质
CN113141305B (zh) * 2021-05-31 2021-11-23 深圳华云信息系统有限公司 通信方法、装置、电子设备和计算机可读存储介质
CN114095567B (zh) * 2021-10-12 2023-12-29 鸬鹚科技(深圳)有限公司 数据访问请求的处理方法、装置、计算机设备及介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101427497A (zh) * 2005-08-30 2009-05-06 思科技术公司 基于实时拥塞反馈来更新最佳路径的方法
US20100165987A1 (en) * 2008-12-26 2010-07-01 Fujitsu Limited Communication device, system and method to form communication route
CN102075424A (zh) * 2011-01-11 2011-05-25 华中科技大学 一种基于反馈更新机制的可信路由方法
CN106231633A (zh) * 2016-10-10 2016-12-14 广东工业大学 一种Ad hoc通信网络优化方法及系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6894991B2 (en) * 2000-11-30 2005-05-17 Verizon Laboratories Inc. Integrated method for performing scheduling, routing and access control in a computer network
DE102006041058B4 (de) * 2006-09-01 2008-09-11 Nokia Siemens Networks Gmbh & Co.Kg Verfahren zur Nachführung von Netzparametern
CN102136994B (zh) * 2010-08-02 2014-04-30 华为技术有限公司 一种建立标签交换路径的方法、系统和节点设备
RU2621728C1 (ru) * 2013-08-01 2017-06-07 Хуавэй Текнолоджиз Ко., Лтд. Способ и устройство управления мощностью восходящей линии связи
CN104579567B (zh) * 2015-01-08 2018-10-12 无锡清华信息科学与技术国家实验室物联网技术中心 逆向路径的编码方法和装置
WO2018112877A1 (zh) * 2016-12-23 2018-06-28 深圳前海达闼云端智能科技有限公司 路径计算和访问请求分发方法、装置及系统
CN108347376B (zh) * 2017-01-24 2020-01-31 华为技术有限公司 一种调整转发路径的方法、装置及系统
US20180324082A1 (en) * 2017-05-05 2018-11-08 Fang Hao Weight setting using inverse optimization
WO2019061169A1 (zh) * 2017-09-28 2019-04-04 深圳前海达闼云端智能科技有限公司 一种基于混合资源的路由选路方法、装置和服务器

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101427497A (zh) * 2005-08-30 2009-05-06 思科技术公司 基于实时拥塞反馈来更新最佳路径的方法
US20100165987A1 (en) * 2008-12-26 2010-07-01 Fujitsu Limited Communication device, system and method to form communication route
CN102075424A (zh) * 2011-01-11 2011-05-25 华中科技大学 一种基于反馈更新机制的可信路由方法
CN106231633A (zh) * 2016-10-10 2016-12-14 广东工业大学 一种Ad hoc通信网络优化方法及系统

Also Published As

Publication number Publication date
US20200177496A1 (en) 2020-06-04
CN108064439B (zh) 2021-04-06
US11146482B2 (en) 2021-10-12
CN108064439A (zh) 2018-05-22

Similar Documents

Publication Publication Date Title
WO2019075642A1 (zh) 一种网络路径优化方法、系统、控制服务端以及入网端
CN105515915B (zh) 节点探测方法及装置、路径选取方法及装置、及网络系统
US11757765B2 (en) Intelligent routing of network packets on telecommunication devices
WO2018152919A1 (zh) 一种路径选取方法及系统、网络加速节点及网络加速系统
WO2017161762A1 (zh) 数据传输方法、装置及系统
CN110381162B (zh) 一种业务处理的方法以及相关装置
US11811638B2 (en) Adaptable software defined wide area network application-specific probing
CN107277013A (zh) 对等网络中的直播系统及节点管理方法
US20210044509A1 (en) Intelligent Edge Gateway Device with Path and Response Time Optimization
CN104580013A (zh) 一种快速选择接入点的网络通信方法及其系统
TW202127930A (zh) 用來在多存取點網路中進行用戶端操縱控制的方法及設備
US11218910B2 (en) First node and a second node and methods of operating the same
CN113518125A (zh) 离线数据的上传方法及系统、存储介质、电子装置
US10348597B2 (en) Monitoring server, resolution server, request device, and node selection method
CN110380981B (zh) 一种流量分发方法及设备
CN105049543A (zh) 智能路由器间穿越非对称nat进行p2p通信的系统及方法
CN111757389B (zh) 一种通信装置和方法
CN103188132A (zh) 基于内容分发网络的即时通讯方法及系统
CN106686034B (zh) Cdn调度增强方法、装置及系统
CN106357478A (zh) 一种服务器集群监控方法及系统
CN113556291B (zh) 流量跟踪方法、装置、设备及计算机可读介质
US20190007851A1 (en) Sdn-based multiple wireless network integration system and method therefor
Xu et al. Minimizing multi-controller deployment cost in software-defined networking
CN111818134B (zh) 变电站数据中心内基于雾计算的数据传输方法及装置
KR102145579B1 (ko) 서버와 클라이언트간 데이터 전송 시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17928987

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC ( EPO FORM 1205A DATED 16/09/2020 )

122 Ep: pct application non-entry in european phase

Ref document number: 17928987

Country of ref document: EP

Kind code of ref document: A1