Network energy consumption and throughput combined optimization routing method based on deep reinforcement learning

Abstract

The invention discloses a network energy consumption and throughput combined optimization routing method based on deep reinforcement learning, and the method comprises the steps: firstly describing the routing scheduling of a data center network as a mixed integer nonlinear programming problem with two targets, namely maximizing the network throughput and minimizing the energy consumption; secondly, generating a large amount of training data for a deep reinforcement learning algorithm, wherein the training data mainly comprise a current network state, a decision behavior, an award and a new network state; and finally, a convolutional neural network and a full-connection neural network are selected as intelligent agents, training operation is performed on the intelligent agents by using training data, and the core theory is to select a Bellman equation to evaluate the result of each behavior, define a Bellman error as a loss function, and optimize the loss function through a gradient descent method until convergence. The method provided by the invention is suitable for a large-scale and high-dynamic data center network, and has the advantages of high efficiency and low cost compared with other schemes (such as Pareto optimum).

Description

technical field [0001] The invention relates to a network energy consumption and throughput joint optimization routing method based on deep reinforcement learning, and belongs to the technical field of optical network communication. Background technique [0002] With the continuous development of the information society, people's demand for information services is increasing day by day, a large number of high-traffic applications have emerged and the demand for traffic has increased exponentially. At the same time, due to the continuous emergence of new network applications, network energy consumption and throughput Volume has become a key factor affecting data center network (DCN) network performance. Especially when a large number of differentiated services are connected to the data center network, an efficient routing and scheduling strategy is a necessary means. [0003] For this reason, it has very practical application value to study the efficient routing scheduling s...

AI Technical Summary

Problems solved by technology

However, DCN is a complex dynamic system, and RL-based routing algorithms need to be continuously learned and trained for different network scenarios, which will greatly increase network overhead

Images