CN-116366460-B - Transmission path determining method and device, electronic equipment and storage medium

Abstract

The application discloses a transmission path determining method, which comprises the steps of determining a predicted performance value of each network node in a plurality of network nodes in a preset period by adopting a preset model according to a historical network diagram of a historical period, wherein the historical network diagram comprises an adjacency weight value among the network nodes and a historical performance value of each network node in the historical period, the historical period corresponds to the preset period, determining a link weight value of each link in the preset period among the network nodes at least according to the predicted performance value of each network node, wherein the link weight value is used for representing the transmission performance of the links, and determining a transmission path used for transmitting service data in the preset period according to the link weight value of each link, wherein the transmission path comprises at least one link. The application also discloses a transmission path determining device, electronic equipment and a storage medium.

Inventors

• XU JUAN
• WANG JINJIANG

Assignees

• 中移（杭州）信息技术有限公司
• 中国移动通信集团有限公司

Dates

Publication Date

20260505

Application Date

20211228

Claims (20)

1. 1. A transmission path determining method, the method comprising: Determining a predicted performance value of each network node in a plurality of network nodes in a preset period by adopting a preset model according to a historical network diagram of a historical period, wherein the historical network diagram comprises an adjacency weight value among the network nodes and a historical performance value of each network node in the historical period, and the historical period corresponds to the preset period; determining a criticality of each link between the network nodes according to the predicted performance values of the network nodes, wherein the criticality is positively correlated with the congestion degree of the links; Determining a cost weight of each link according to transmission performance parameters of each link, wherein the transmission performance parameters comprise inherent transmission characteristics of the links; Determining a link weight of the link in the preset period according to the criticality of the link and the cost weight, wherein the link weight is used for representing the transmission performance of the link; And determining a transmission path for transmitting service data in the preset time period according to the link weight value of each link, wherein the transmission path comprises at least one link.
2. 2. The method of claim 1, wherein the determining, according to the historical network map of the historical time period, the predicted performance value of each of the plurality of network nodes in the predetermined time period using the preset model includes: and determining the predicted performance value of each network node in the network nodes in a plurality of different preset time periods by adopting a space-time diagram convolution neural network model according to the historical network diagrams of the historical time periods.
3. 3. The method of claim 1, wherein the expression for the adjacency weight value between the network nodes is: Wherein, the Representing the value of the adjacency weight, And In order to set the value of the preset value, And Representing the sequence number of the network node, Indicating number of Is the network node to sequence number Is provided for the network node.
4. 4. The method of claim 1, wherein said determining criticality of each link between the network nodes based on the predicted performance values of the network nodes comprises: determining a predicted load of each link between the network nodes according to the predicted performance values of the network nodes; determining the criticality of the link as the quotient of the predicted load of the link divided by the total capacity of the link.
5. 5. The method of claim 1, wherein, The expression for determining the cost weight of the link is: Wherein, the The cost weight representing the link, Indicating that the link has occupied bandwidth, Representing the time delay of the link in question, Indicating the bandwidth utilization of the link in question, Indicating the packet loss rate of the link, 、 、 And Is a weight factor, wherein, 。
6. 6. The method of claim 1, wherein, The expression for determining the link weight is: Wherein, the Representing the weight of the link in question, The cost weight representing the link, Representing the criticality of the link, And And weight factors respectively representing the cost weight and the criticality.
7. 7. The method of claim 1, wherein the determining a transmission path for transmitting traffic data according to the link weight of each link comprises: And determining a transmission path for transmitting service data by adopting a Dijiestra algorithm according to the link weight of each link.
8. 8. The method of claim 1, wherein the determining a transmission path for transmitting traffic data according to the link weight of each link comprises: And determining a transmission path of the service data based on the priority of the service data, wherein the sum of link weights of the links in the transmission path corresponding to the service data of the first priority is smaller than the sum of link weights of the links in the transmission path corresponding to the service data of the second priority, and the first priority is higher than the second priority.
9. 9. The method of claim 1, wherein, And the cost weight of the link included in the transmission path is smaller than the cost weight threshold of the service type corresponding to the service data.
10. 10. A transmission path determining apparatus, characterized by comprising: The first determining module is used for determining a predicted performance value of each network node in a plurality of network nodes in a preset period by adopting a preset model according to a historical network diagram of a historical period, wherein the historical network diagram comprises an adjacency weight value among the network nodes and a historical performance value of each network node in the historical period, and the historical period corresponds to the preset period; The system comprises a first determining module, a second determining module, a link weight and a link control module, wherein the first determining module is used for determining the key degree of each link between network nodes according to the predicted performance values of the network nodes, determining the cost weight of each link according to the transmission performance parameters of the links, and determining the link weight of the links in the preset time period according to the key degree of the links and the cost weight, wherein the key degree is positively related to the congestion degree of the links, and the transmission performance parameters comprise inherent transmission characteristics of the links; and a third determining module, configured to determine a transmission path for transmitting service data in the predetermined period according to a link weight of each link, where the transmission path includes at least one link.
11. 11. The apparatus of claim 10, wherein the first determination module is configured to And determining the predicted performance value of each network node in the network nodes in a plurality of different preset time periods by adopting a space-time diagram convolution neural network model according to the historical network diagrams of the historical time periods.
12. 12. The apparatus of claim 10, wherein the expression for the adjacency weight value between the network nodes is: Wherein, the Representing the value of the adjacency weight, And In order to set the value of the preset value, And Representing the sequence number of the network node, Indicating number of Is the network node to sequence number Is provided for the network node.
13. 13. The apparatus of claim 10, wherein the second determining module is specifically configured to: determining a predicted load of each link between the network nodes according to the predicted performance values of the network nodes; determining the criticality of the link as the quotient of the predicted load of the link divided by the total capacity of the link.
14. 14. The apparatus of claim 10, wherein, The expression for determining the cost weight of the link is: Wherein, the The cost weight representing the link, Indicating that the link has occupied bandwidth, Representing the time delay of the link in question, Indicating the bandwidth utilization of the link in question, Indicating the packet loss rate of the link, 、 、 And Is a weight factor, wherein, 。
15. 15. The apparatus of claim 10, wherein, The expression for determining the link weight is: Wherein, the Representing the weight of the link in question, The cost weight representing the link, Representing the criticality of the link, And And weight factors respectively representing the cost weight and the criticality.
16. 16. The apparatus of claim 10, wherein the third determining module is specifically configured to: And determining a transmission path for transmitting service data by adopting a Dijiestra algorithm according to the link weight of each link.
17. 17. The apparatus of claim 10, wherein the third determining module is specifically configured to: And determining a transmission path of the service data based on the priority of the service data, wherein the sum of link weights of the links in the transmission path corresponding to the service data of the first priority is smaller than the sum of link weights of the links in the transmission path corresponding to the service data of the second priority, and the first priority is higher than the second priority.
18. 18. The apparatus of claim 10, wherein the transmission path comprises a cost weight for the link that is less than a cost weight threshold for the traffic data corresponding to a traffic type.
19. 19. A storage medium storing an executable program, wherein the executable program, when executed by a processor, implements the steps of the transmission path determination method according to any one of claims 1 to 9.
20. 20. An electronic device comprising a memory, a processor and an executable program stored on the memory and executable by the processor, wherein the processor performs the steps of the transmission path determination method according to any one of claims 1 to 9 when the executable program is run.

Description

Transmission path determining method and device, electronic equipment and storage medium Technical Field The present invention relates to the field of network traffic engineering, and in particular, to a transmission path determining method, apparatus, electronic device, and storage medium. Background The data center network is used as a platform for cloud computing, virtualization and big data service, the network scale is continuously enlarged, the transmitted flow is increased in an explosive manner, the flow characteristics are complex and various and difficult to manage, and network congestion is easily caused. Maldistribution of network resources is one of the main causes of network congestion, and how to manage network data flows is important to find an optimal transmission path for the data flows. Therefore, the congestion problem caused by unbalanced network load is relieved, the running reliability of the network is guaranteed, and the realization of the link load balancing strategy becomes a core problem in the key technology of network optimization. Disclosure of Invention The embodiment of the application provides a transmission path determining method, a transmission path determining device, electronic equipment and a storage medium. The technical scheme of the embodiment of the application is realized as follows: According to a first aspect of an embodiment of the present application, there is provided a transmission path determining method, including: Determining a predicted performance value of each network node in a plurality of network nodes in a preset period by adopting a preset model according to a historical network diagram of a historical period, wherein the historical network diagram comprises an adjacency weight value among the network nodes and a historical performance value of each network node in the historical period, and the historical period corresponds to the preset period; determining a link weight of each link between the network nodes in the preset time period at least according to the predicted performance value of each network node, wherein the link weight is used for representing the transmission performance of the link; And determining a transmission path for transmitting service data in the preset time period according to the link weight value of each link, wherein the transmission path comprises at least one link. In one embodiment, the determining, according to the historical network graph of the historical period, the predicted performance value of each network node in the plurality of network nodes in the predetermined period by using a preset model includes: and determining the predicted performance value of each network node in the network nodes in a plurality of different preset time periods by adopting a space-time diagram convolution neural network model according to the historical network diagrams of the historical time periods. In one embodiment, the expression of the adjacency weight value between the network nodes is: wherein W ij represents the adjacency weight value, σ 2 and ε are preset values, i and j represent the sequence numbers of the network nodes, and d ij represents the distance from the network node with sequence number i to the network node with sequence number j. In one embodiment, the determining the link weight of each link between the network nodes for the predetermined period of time at least according to the predicted performance values of the network nodes includes: determining a criticality of each link between the network nodes according to the predicted performance values of the network nodes, wherein the criticality is positively correlated with the congestion degree of the links; Determining a cost weight of each link according to the transmission performance parameters of each link; And determining the link weight of the link in the preset period according to the criticality of the link and the cost weight. In one embodiment, the determining the criticality of each link between the network nodes according to the predicted performance values of the network nodes includes: determining a predicted load of each link between the network nodes according to the predicted performance values of the network nodes; determining the criticality of the link as the quotient of the predicted load of the link divided by the total capacity of the link. In one embodiment, the expression that determines the cost weight for the link is: σp＝αbp+βdp+μrp+λlp Wherein σ p represents the cost weight of the link, b p represents the occupied bandwidth of the link, d p represents the time delay of the link, r p represents the bandwidth utilization rate of the link, l p represents the packet loss rate of the link, and α, β, μ and λ are weight factors, wherein α+β+μ+λ=1. In one embodiment, the expression determining the link weight is: Wp＝w1σp+w2ρp Wherein W p represents the link weight, σ p represents the cost weight of the link, ρ p represents the criticalit