Electric power communication network routing method based on deep reinforcement learning

Abstract

The invention discloses an electric power communication network routing method based on deep reinforcement learning. The method aims at an electric power communication network route selection strategybased on SDN architecture; an SDN-based power communication network system structure is analyzed; and a routing method based on deep reinforcement learning (DDPG) is designed, and a deep reinforcement learning module is repeatedly trained by taking service bandwidth, time delay and packet loss rate requirements as reward values to realize routing strategy optimization.

Description

technical field [0001] The invention belongs to the field of electric power communication, and in particular relates to a power communication network routing method based on deep reinforcement learning. Background technique [0002] In recent years, smart grid and SDN (Software-Defined Networks) technology have been developing continuously; smart grid relies on power communication network for efficient information transmission and interaction, and the decoupling characteristics of SDN technology data plane and control plane can simplify Network configuration and management, and flexible flow control; the SDN controller has a global network view, which can reasonably allocate transmission resources according to business needs. Therefore, building an SDN-based power communication network is a future development trend; while traditional static routing algorithms converge faster Disadvantages such as slowness are not applicable to power communication networks based on SDN archit...

AI Technical Summary

Problems solved by technology

However, none of the above studies considered the particularity of power communication service transmission bandwidth, delay and reliability requirements, and could not meet the service transmission requirements of power communication network based on SDN architecture.

Images