Adversarial Reinforcement Learning-Based Converged Communication Efficiency Improvement Method for Power Distribution Network

In order to satisfy the diversified communication requirements of terminal source nodes in power distribution network, it is necessary to optimize the communication orchestration in power distribution unified communication network. Firstly, we construct the joint optimization problem of data transmi...

Full description

Saved in:
Bibliographic Details
Main Authors: Linyu PENG, Xu LIU, Wei TANG, Qing LIU, Hao FANG, Guanghui ZHANG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2023-09-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202210068
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to satisfy the diversified communication requirements of terminal source nodes in power distribution network, it is necessary to optimize the communication orchestration in power distribution unified communication network. Firstly, we construct the joint optimization problem of data transmission delay and energy consumption. Then, the joint optimization problem is modeled as a multi-armed bandit problem, and an adversarial reinforcement learning-based communication orchestration algorithm for power distribution unified communication network is proposed, which uses the historical orchestration information and the perceived adversary between source nodes to dynamically learn the communication orchestration strategy. Finally, the superior performance of the proposed algorithm is verified through simulation.
ISSN:1004-9649