Voltage Control Based on Multi-Agent Safe Deep Reinforcement Learning

To address issues of voltage limit violations and fluctuations caused by the high penetration of distributed photovoltaic (PV) systems in the distribution network, a voltage control method based on multi-agent safe deep reinforcement learning is proposed. The voltage control with PV is modeled as a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi ZENG, Yi ZHOU, Jixiang LU, Liangcai ZHOU, Ningkai TANG, Hong LI
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2025-02-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202404047
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850070339556474880
author Yi ZENG
Yi ZHOU
Jixiang LU
Liangcai ZHOU
Ningkai TANG
Hong LI
author_facet Yi ZENG
Yi ZHOU
Jixiang LU
Liangcai ZHOU
Ningkai TANG
Hong LI
author_sort Yi ZENG
collection DOAJ
description To address issues of voltage limit violations and fluctuations caused by the high penetration of distributed photovoltaic (PV) systems in the distribution network, a voltage control method based on multi-agent safe deep reinforcement learning is proposed. The voltage control with PV is modeled as a decentralized partially observable Markov decision process. A safety layer is introduced in the deep policy network for agent design, while the voltage barrier function based on traditional optimization model voltage constraints is used in defining the agent reward function. Testing results on the IEEE 33-bus system demonstrate that the proposed method can generate voltage control strategies that meet safety constraints under high photovoltaic penetration scenarios, and it can be used to assist dispatchers in making real-time decisions online.
format Article
id doaj-art-9f46da15344c40daaab68a45a373fbea
institution DOAJ
issn 1004-9649
language zho
publishDate 2025-02-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-9f46da15344c40daaab68a45a373fbea2025-08-20T02:47:33ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492025-02-0158211111710.11930/j.issn.1004-9649.202404047zgdl-58-02-zengyiVoltage Control Based on Multi-Agent Safe Deep Reinforcement LearningYi ZENG0Yi ZHOU1Jixiang LU2Liangcai ZHOU3Ningkai TANG4Hong LI5State Grid Electric Power Research Institute (NARI Group Corporation), Nanjing 211106, ChinaEast China Branch of State Grid Corporation of China, Shanghai 200120, ChinaState Grid Electric Power Research Institute (NARI Group Corporation), Nanjing 211106, ChinaEast China Branch of State Grid Corporation of China, Shanghai 200120, ChinaState Grid Electric Power Research Institute (NARI Group Corporation), Nanjing 211106, ChinaState Grid Electric Power Research Institute (NARI Group Corporation), Nanjing 211106, ChinaTo address issues of voltage limit violations and fluctuations caused by the high penetration of distributed photovoltaic (PV) systems in the distribution network, a voltage control method based on multi-agent safe deep reinforcement learning is proposed. The voltage control with PV is modeled as a decentralized partially observable Markov decision process. A safety layer is introduced in the deep policy network for agent design, while the voltage barrier function based on traditional optimization model voltage constraints is used in defining the agent reward function. Testing results on the IEEE 33-bus system demonstrate that the proposed method can generate voltage control strategies that meet safety constraints under high photovoltaic penetration scenarios, and it can be used to assist dispatchers in making real-time decisions online.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202404047volt-var controlsafe deep reinforcement learningmulti-agent
spellingShingle Yi ZENG
Yi ZHOU
Jixiang LU
Liangcai ZHOU
Ningkai TANG
Hong LI
Voltage Control Based on Multi-Agent Safe Deep Reinforcement Learning
Zhongguo dianli
volt-var control
safe deep reinforcement learning
multi-agent
title Voltage Control Based on Multi-Agent Safe Deep Reinforcement Learning
title_full Voltage Control Based on Multi-Agent Safe Deep Reinforcement Learning
title_fullStr Voltage Control Based on Multi-Agent Safe Deep Reinforcement Learning
title_full_unstemmed Voltage Control Based on Multi-Agent Safe Deep Reinforcement Learning
title_short Voltage Control Based on Multi-Agent Safe Deep Reinforcement Learning
title_sort voltage control based on multi agent safe deep reinforcement learning
topic volt-var control
safe deep reinforcement learning
multi-agent
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202404047
work_keys_str_mv AT yizeng voltagecontrolbasedonmultiagentsafedeepreinforcementlearning
AT yizhou voltagecontrolbasedonmultiagentsafedeepreinforcementlearning
AT jixianglu voltagecontrolbasedonmultiagentsafedeepreinforcementlearning
AT liangcaizhou voltagecontrolbasedonmultiagentsafedeepreinforcementlearning
AT ningkaitang voltagecontrolbasedonmultiagentsafedeepreinforcementlearning
AT hongli voltagecontrolbasedonmultiagentsafedeepreinforcementlearning