Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters

Kang Xiong; Chengjin Ye; Bin Liu; Xun Suo

doi:10.1049/enc2.70026

欢迎来到能源电力期刊网！

您当前的位置：

首页 >

文章列表页 >

Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters

更新时间：2026-03-24

- Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters
- Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters
- Energy Conversion and Economics 2025年6卷第6期
- 作者机构：
  
  1. College of Electrical Engineering, Zhejiang University,Hangzhou,China
  2. Contribution: Conceptualization, Methodology, Resources, Software, Writing - original draft
  3. Contribution: Conceptualization, Methodology, Resources, Supervision, Writing - review & editing
  4. The Electric Power Research Institute of CSG Guizhou Power Grid Co., Ltd.,Guiyang,China
  5. Contribution: Formal analysis, Methodology, Writing - review & editing
- 作者简介：
- 基金信息：
- DOI：10.1049/enc2.70026
  中图分类号：
- 纸质出版：2025
- 稿件说明：
移动端阅览
Kang Xiong, Chengjin Ye, Bin Liu, 等. Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters[J]. Energy Conversion and Economics, 2025,6(6).

Kang Xiong, Chengjin Ye, Bin Liu, et al. Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters[J]. Energy Conversion and Economics, 2025, 6(6).
Kang Xiong, Chengjin Ye, Bin Liu, 等. Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters[J]. Energy Conversion and Economics, 2025,6(6). DOI： 10.1049/enc2.70026.

Kang Xiong, Chengjin Ye, Bin Liu, et al. Multi-agent deep reinforcement learning-enabled voltage regulation approach for partitioned active distribution network using heterogeneous PV inverters[J]. Energy Conversion and Economics, 2025, 6(6). DOI： 10.1049/enc2.70026.

摘要

Abstract

To improve the adaptability of voltage regulation in active distribution networks (ADNs) with high photovoltaic (PV) penetration

this paper proposes a distributed Volt/Var control (VVC) strategy enabled by multi-agent deep reinforcement learning and implemented through heterogeneous PV inverters. First

a distributed VVC framework is established by partitioning the ADN into multiple sub-networks

each modelled as an agent

with the goal of minimizing voltage deviation. This control framework considers the heterogeneous operation modes of PV systems and utilizes both reactive power support and active power curtailment to maintain voltage within acceptable limits. Then

the VVC problem is formulated as a Markov game and solved using a multi-agent soft actor–critic algorithm. Simulation studies conducted on the IEEE 33-bus and 118-bus test systems validated the effectiveness of the proposed method

demonstrating its superior performance in reducing voltage fluctuations compared to benchmark approaches.

关键词

Keywords

references

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

Active distribution network dynamic partitioning method based on the Voltage/Var sensitivity using branch cutting and binary particle swarm optimisation