An optimal path selection algorithm based on machine learning under SDN

Abstract

The invention discloses an optimal path selection algorithm based on machine learning under SDN. The method comprises steps of building SDN platform, SIMULATING REALITY NETWORK ENVIRONMENT, acquiringdiscrete real-time network state data; carrying out classification according to different QoS index requirements of different services in network transmission; obtaining a plurality of indexes, arranging experimental data to obtain a sample data set, screening an optimal path from the sample data set by using a heuristic algorithm according to consideration standards of different services on eachindex, labeling the optimal path corresponding to each group of data, and finally training the data set by using a machine learning algorithm to obtain a classifier, thereby achieving the purpose of rapid dynamic routing. The result of the method is basically the same as the optimization result of the heuristic algorithm, and the calculation time of the model is far shorter than that of the heuristic algorithm, so that the necessary condition of rapid decision making in actual network operation is met. Compared with a particle swarm algorithm, the extreme learning machine algorithm has the advantages that the cpu operation time required by calculation is greatly shortened, and the real network deployment requirement can be completely met.

Description

technical field [0001] The present invention relates to the problem that the general routing method under the software-defined network architecture will generate relatively high time cost, and proposes a low-time-consuming multi-constraint QoS routing planning method, specifically relating to a machine-learning-based optimal routing method under SDN optimal path selection algorithm. Background technique [0002] According to the 42nd "Statistical Report on Internet Development in China" released by the China Internet Network Information Center, as of June 2018, the number of Internet users in my country has reached 802 million, and the number of mobile users has reached 788 million. And with the rapid development of information technology and the continuous emergence of emerging technologies such as cloud computing and big data, network data has shown explosive growth in terms of both scale and type. Ubiquitous network access and large bandwidth make the dynamic management ...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to significantly reduce the time consumption of the algorithm in order to meet the different requirements of multiple QoS indicators in different services, solve the problem of introducing high time cost in the existing algorithm, and propose a machine learning-based optimal solution under SDN. The optimal path selection algorithm can solve the fast dynamic routing of different business flows

Images