Method and device for determining traffic transmission strategy

Abstract

The embodiment of the invention provides a method and device for determining a flow transmission strategy, and the method comprises the steps: obtaining first communication states of all node pairs ina software-defined network, wherein each node pair comprises two nodes in communication connection, and at least one transmission path exists between the two nodes of each node pair; inputting the first communication states of all the node pairs into a preset learning model to obtain a control action of each node pair, with the control action comprising a load proportion of each transmission pathcorresponding to the node pair, and the preset learning model being a model obtained by training a deep reinforcement learning network based on a preset training set; and based on the control actionof each node pair, generating a flow transmission strategy corresponding to the node pair. Through the method, the flow transmission adjustment efficiency is improved, and the ductility and the accuracy of the determination mode of the flow transmission strategy are improved.

Description

technical field [0001] The present invention relates to the technical field of communications, in particular to a method and device for determining a traffic transmission strategy. Background technique [0002] With the rapid development of computer networks, network services are increasingly diversified, and traffic is growing explosively. In order to improve the traffic transmission efficiency in the entire network, it is necessary to adjust the traffic transmission strategy in each communication device in real time, so that the communication device transmits traffic based on the adjusted traffic transmission strategy, and then optimize the traffic transmission efficiency in the entire network. [0003] Currently, there are several ways to determine the common traffic transmission policy as follows. [0004] In the first type, the network administrator manually configures corresponding traffic transmission policies on different communication devices. When the traffic tra...

AI Technical Summary

Problems solved by technology

However, whenever the traffic load in the network changes, the network administrator needs to modify the traffic transmission strategy accordingly in the control application. SDN cannot modify the traffic transmission strategy according to the traffic load in the network by itself, making the traffic transmission adjustment inefficient

Images