Traffic engineering method applied to segmented routing network environment

Abstract

The invention provides a traffic engineering method applied to a segmented routing network environment, which is used for planning the path of each flow according to the traffic demand of the network environment, and comprises the following steps: S1, obtaining the traffic demand in the segmented routing environment; s2, selecting candidate routing nodes from all routing nodes of the network environment by adopting a pre-trained strategy model; wherein the strategy model is a model which is obtained by taking traffic matrixes corresponding to all routing nodes as input states, selecting candidate nodes as output actions and taking a historical traffic matrix and a network adjacency matrix as sample data through training; and S3, carrying out linear programming by using the candidate routing nodes selected in the step S2. According to the method, the calculation speed of a traditional traffic engineering scheme based on a linear programming method in a segmented routing environment can be effectively improved while the performance is close to that of an original model.

Description

technical field [0001] The invention belongs to the technical field of traffic engineering, in particular, to the field of traffic engineering based on linear programming in a segmented routing environment, and more specifically, to a traffic engineering method applied to a segmented routing network environment and applied to a segmented routing environment. A policy model for traffic engineering acceleration in a routed network environment. Background technique [0002] With the rapid development of the Internet, the scale and complexity of the network continue to increase, and the network traffic grows explosively, which puts forward higher requirements for the network carrying capacity and service quality. Therefore, how to optimize network traffic and ensure service quality has become a key issue. The representative technology used to optimize network traffic is Traffic Engineering (TE). Improve the overall performance of the network. [0003] Software Defined Network ...

AI Technical Summary

Problems solved by technology

[0007]2) SR traffic engineering methods based on heuristic methods, which use heuristic algorithms to calculate traffic engineering decisions, often have faster speed but performance is not as good as mathematics method of planning

[0008] Among them, the SR traffic engineering method based on mathematical programming is more commonly used. However, the existing SR traffic engineering method based on mathematical programming has serious scalability problems: Since traffic engineering methods in reality are usually executed periodically at intervals of several minutes, as the network scale increases, the number of parameters in the linear programming model and the solution time also increase rapidly, and it is often impossible to find out in a reasonable time Optimization results, resulting in delayed execution of traffic engineering

Images