Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning

Xiaowei Pu; Hao Xiao; Wei Pei; Yanhong Yang; Li Ma; Tengfei Ma; Shuai Zhang

doi:10.17775/CSEEJPES.2023.05920

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning

Special Section Papers | 更新时间：2026-10-10

- Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning
- Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning
- 中国电机工程学会电力与能源系统学报(英文) 2026年12卷第5期页码：2209-2220
- 作者机构：
  
  Institute of Electrical Engineering, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China
- 作者简介：
- 基金信息：
- DOI：10.17775/CSEEJPES.2023.05920
  中图分类号：
- 纸质出版：2026-09-01
- 稿件说明：
移动端阅览
Xiaowei Pu, Hao Xiao, Wei Pei, 等. Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning[J]. 中国电机工程学会电力与能源系统学报(英文), 2026,12(5):2209-2220.

Xiaowei Pu, Hao Xiao, Wei Pei, et al. Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning[J]. CSEE Journal of Power and Energy Systems, 2026, 12(5): 2209-2220.
Xiaowei Pu, Hao Xiao, Wei Pei, 等. Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning[J]. 中国电机工程学会电力与能源系统学报(英文), 2026,12(5):2209-2220. DOI： 10.17775/CSEEJPES.2023.05920.

Xiaowei Pu, Hao Xiao, Wei Pei, et al. Optimal Energy Management of Networked Multi-Energy Microgrids Based on Improved Multi-Agent Federated Reinforcement Learning[J]. CSEE Journal of Power and Energy Systems, 2026, 12(5): 2209-2220. DOI： 10.17775/CSEEJPES.2023.05920.

摘要

Abstract

The energy management of the networked multi-energy microgrids (MEMGs) contributes to promoting the consumption of renewable energy and balancing the different interests of multi-agent MEMG systems. A novel energy management method of MEMG system based on improved multi-agent federated reinforcement learning is proposed. First

this study establishes the optimization model of MEMG system considering multi-party economic benefits in P2P trading market. To solve the problems of gradient instability and low learning efficiency in traditional federated reinforcement learning with FedAvg federation strategy

a novel Federated Attention-based Multi-agent Deep Deterministic policy gradient (FA-MADDPG) framework is proposed for real-time scheduling optimization of MEMG system. In addition

this study proposes an agent exploration mechanism based on directional noise to achieve the SoC balance of distributed energy storage before and after scheduling. Finally

a numerical example is given to verify the effectiveness of the proposed method. Compared with MADDPG and federated MADDPG method

the proposed method has better convergence and energy scheduling ability

and the economic cost is reduced by 13.57% and 10.22% respectively.

关键词

Keywords

references

26. Leo. Project LEO -local energy oxfordshire. [Online]. Available: https://project-leo.co.uk/

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Two-time-scale Congestion Management Scheme for Microgrid Integrated Distribution Networks

Coordinated Optimal Dispatching Approach for Integrated Energy System Cluster Based on Improved Deep Reinforcement Learning

Economic Dispatch in Microgrids with Photovoltaic and Load Communication Failures Using Deep Reinforcement Learning with Relative Entropy Regularized Asynchronous Update

Real-time Energy Management of Low-carbon Ship Microgrid Based on Data-driven Stochastic Model Predictive Control

Deep Reinforcement Learning Based Bi-layer Optimal Scheduling for Microgrids Considering Flexible Load Control