Load balancing method based on graph convolutional neural network and deep reinforcement learning

Abstract

The invention discloses a load balancing method based on a graph convolutional neural network and deep reinforcement learning. The load balancing algorithm based on the graph convolutional neural network and deep reinforcement learning comprises the following steps: acquiring a network state undirected graph, wherein the network state undirected graph comprises a characteristic matrix of switches and data link load weight information between the switches; obtaining stream information; obtaining a trained DQN decision model; and inputting the flow information and the network state undirected graph into the DQN decision model to obtain a decision action. According to the method, deep reinforcement learning and the graph convolutional neural network are combined and applied to a load balancing algorithm, so that the model can make a decision according to state information, the topological structure of the network is considered as a decision factor, the model can make a decision according to a more comprehensive network state, and the decision performance of the model is improved.

Description

technical field [0001] This application relates to the technical field of SDN data center network, and specifically relates to a load balancing method based on graph convolutional neural network and deep reinforcement learning and a load balancing device based on graph convolutional neural network and deep reinforcement learning. Background technique [0002] With the rapid development of information technology, we have entered an era of data explosion. There are more and more information and data in the network, such as images, videos, texts, and voices. Users on the Internet provide a variety of services, and the data interaction generated by these services requires the support of the data center network. There are multiple paths between different pairs of hosts in the data center network. Due to the dynamic nature of the data center network, the uncertainty is large. The load balancing algorithm selects the appropriate path to route the flow in the network, so that the da...

AI Technical Summary

Problems solved by technology

However, limited by the overhead of calculating routing paths and the dynamics of network traffic, the load balancing algorithm in the network still has problems such as slow response and large amount of calculation.

Images