Decentralized Coordinated Control Strategy for Power Quality in Low Voltage Distribution Networks Based on Multi-agent Deep Reinforcement Learning

OU Jieyu; ZHANG Yi; XIN Rong; CHEN Yunfei; LIN Yan

doi:10.13334/j.0258-8013.pcsee.241754

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Decentralized Coordinated Control Strategy for Power Quality in Low Voltage Distribution Networks Based on Multi-agent Deep Reinforcement Learning

更新时间：2026-02-01

- Decentralized Coordinated Control Strategy for Power Quality in Low Voltage Distribution Networks Based on Multi-agent Deep Reinforcement Learning
- Issue 21, Pages: 8308-8322(2025)
- 作者机构：
  
  1. 福州大学电气工程与自动化学院,福建省,福州市,350108
  2. 国网福建省电力有限公司电力科学研究院,福建省,福州市,350007
- 作者简介：
- 基金信息：
- DOI：10.13334/j.0258-8013.pcsee.241754
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
OU Jieyu, ZHANG Yi, XIN Rong, et al. Decentralized Coordinated Control Strategy for Power Quality in Low Voltage Distribution Networks Based on Multi-agent Deep Reinforcement Learning[J]. 2025, (21): 8308-8322.
DOI：

OU Jieyu, ZHANG Yi, XIN Rong, et al. Decentralized Coordinated Control Strategy for Power Quality in Low Voltage Distribution Networks Based on Multi-agent Deep Reinforcement Learning[J]. 2025, (21): 8308-8322. DOI： 10.13334/j.0258-8013.pcsee.241754.

摘要

随着新型负荷与分布式光伏的广泛接入，低压配电网中电能质量问题日渐凸显。既有电能质量综合调控策略具有难以适应低压配电网通讯条件薄弱、设备计算能力有限与电能质量问题复杂多样等特征，无法满足低压配电网的电能质量治理需求。为此，该文提出一种基于多智能体深度强化学习的低压配电网电能质量分散式协同调控策略。首先，统筹兼顾低压配电网以上典型特征，将电能质量协同调控问题建立为分散式部分可观的马尔科夫决策过程；其次，为解决样本效率低下问题，设计改进深度密连强化学习(modified deep dense reinforcement learning，MD2RL)结构与MATD3-MD2RL算法；再次，引入集中式训练-分散式执行架构，在保证分散式观测的同时实现多智能体协同运行；最后，在改进IEEE-13节点系统与实际低压配电网中进行算例测试。结果表明，所提调控策略可有效改善低压配电网的电能质量，同时具有无通讯、实时性强且不依赖于精确潮流模型等优势。

Abstract

With the extensive integration of novel load demands and distributed PV generations

power quality issues are becoming more prevalent in low voltage distribution networks (LVDNs). Existing control strategies struggle to adapt to LVDNs

which features weak communication conditions

limited computational capacity

and complex power quality issues

thereby failing to meet the power quality needs in LVDNs. Therefore

this paper proposes a decentralized coordinated power quality control strategy for LVDNs based on multi-agent deep reinforcement learning (MADRL). First

considering the typical characteristics of LVDNs

the power quality coordinated control problem is transformed into a decentralized partially observable Markov decision process. Secondly

to address the low sample efficiency

the modified deep dense reinforcement learning (MD2RL) structure and the MATD3-MD2RL algorithm are designed. Then

a centralized training-decentralized execution framework is introduced to ensure decentralized observations while achieving multi-agent coordination. Finally

case studies are conducted on the IEEE 13-bus system and a practical LVDN. The results demonstrate that the proposed control strategy improves the power quality of LVDNs with additional advantages such as independence from communication

strong real-time performance

and no reliance on precise power flow models.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Zonal Voltage Control Strategy Based on Graph Deep Reinforcement Learning With Spatial-temporal Pseudo-twin Network

考虑自注意力和时序记忆的深度强化学习配电网无功电压控制策略

A Data-driven Harmonic Source Modeling Method Based on Joint Time-frequency Feature Extraction

A Distributed PV Active Power Adjustability Evaluation Method Based on Self-adaptive Privacy-preserving Federated Learning

Two-stage Distributed Generators Optimization Based on Deep Reinforcement Learning With Parameter Sharing

Related Author

CUI Yang

ZHU Fu

WANG Yijian

HUANG Siyu

ZHAO Yuting

YANG Mao

刘硕

冯斌

Related Institution

Changchun Power Supply Company, State Grid Jilin Electric Power Company

State Grid Jiangsu Electric Power Company, Xiangshui County Power Supply Branch

Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education (Northeast Electric Power University)

浙江大学电气工程学院

国家电网有限公司华北分部

AI问答

⁰