Coordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement Learning

A safe reinforcement learning method based on offline strategies is proposed. Through offline training of a large amount of historical operating data of the distribution network, it gets rid of the traditional optimization method. Dependence on complete and accurate models. First, combined with the...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao JIAO, Yanyan YIN, Chen WU, Jian LIU, Chunlei XU, Xian XU, Guoqiang SUN
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2024-03-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202311065
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850249808252502016
author Hao JIAO
Yanyan YIN
Chen WU
Jian LIU
Chunlei XU
Xian XU
Guoqiang SUN
author_facet Hao JIAO
Yanyan YIN
Chen WU
Jian LIU
Chunlei XU
Xian XU
Guoqiang SUN
author_sort Hao JIAO
collection DOAJ
description A safe reinforcement learning method based on offline strategies is proposed. Through offline training of a large amount of historical operating data of the distribution network, it gets rid of the traditional optimization method. Dependence on complete and accurate models. First, combined with the distribution network parameter information, an active and reactive power optimization model based on the constrained Markov decision process (CMDP) was established; then, a new safety reinforcement learning method was designed based on the original dual optimization method. The cost function is minimized while maximizing future discount rewards; finally, simulations are performed on power distribution system. The simulation results show that the proposed method can online generate a dispatching strategy that satisfies complex constraints and has economic benefits based on real-time observation information of the distribution network.
format Article
id doaj-art-4f3615c660c3418b87c2dcd03ce72d61
institution OA Journals
issn 1004-9649
language zho
publishDate 2024-03-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-4f3615c660c3418b87c2dcd03ce72d612025-08-20T01:58:24ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492024-03-01573435010.11930/j.issn.1004-9649.202311065zgdl-57-03-jiaohaoCoordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement LearningHao JIAO0Yanyan YIN1Chen WU2Jian LIU3Chunlei XU4Xian XU5Guoqiang SUN6State Grid Jiangsu Electric Power Science Research Institute, Nanjing 211103, ChinaCollege of Electrical and Power Engineering, Hohai University, Nanjing 211100, ChinaState Grid Jiangsu Electric Power Co., Ltd., Nanjing 210024, ChinaState Grid Jiangsu Electric Power Science Research Institute, Nanjing 211103, ChinaState Grid Jiangsu Electric Power Co., Ltd., Nanjing 210024, ChinaState Grid Jiangsu Electric Power Co., Ltd., Nanjing 210024, ChinaCollege of Electrical and Power Engineering, Hohai University, Nanjing 211100, ChinaA safe reinforcement learning method based on offline strategies is proposed. Through offline training of a large amount of historical operating data of the distribution network, it gets rid of the traditional optimization method. Dependence on complete and accurate models. First, combined with the distribution network parameter information, an active and reactive power optimization model based on the constrained Markov decision process (CMDP) was established; then, a new safety reinforcement learning method was designed based on the original dual optimization method. The cost function is minimized while maximizing future discount rewards; finally, simulations are performed on power distribution system. The simulation results show that the proposed method can online generate a dispatching strategy that satisfies complex constraints and has economic benefits based on real-time observation information of the distribution network.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202311065active distribution networkactive and reactive power coordination optimizationsafety reinforcement learning
spellingShingle Hao JIAO
Yanyan YIN
Chen WU
Jian LIU
Chunlei XU
Xian XU
Guoqiang SUN
Coordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement Learning
Zhongguo dianli
active distribution network
active and reactive power coordination optimization
safety reinforcement learning
title Coordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement Learning
title_full Coordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement Learning
title_fullStr Coordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement Learning
title_full_unstemmed Coordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement Learning
title_short Coordinated Optimization of Active and Reactive Power of Active Distribution Network Based on Safety Reinforcement Learning
title_sort coordinated optimization of active and reactive power of active distribution network based on safety reinforcement learning
topic active distribution network
active and reactive power coordination optimization
safety reinforcement learning
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202311065
work_keys_str_mv AT haojiao coordinatedoptimizationofactiveandreactivepowerofactivedistributionnetworkbasedonsafetyreinforcementlearning
AT yanyanyin coordinatedoptimizationofactiveandreactivepowerofactivedistributionnetworkbasedonsafetyreinforcementlearning
AT chenwu coordinatedoptimizationofactiveandreactivepowerofactivedistributionnetworkbasedonsafetyreinforcementlearning
AT jianliu coordinatedoptimizationofactiveandreactivepowerofactivedistributionnetworkbasedonsafetyreinforcementlearning
AT chunleixu coordinatedoptimizationofactiveandreactivepowerofactivedistributionnetworkbasedonsafetyreinforcementlearning
AT xianxu coordinatedoptimizationofactiveandreactivepowerofactivedistributionnetworkbasedonsafetyreinforcementlearning
AT guoqiangsun coordinatedoptimizationofactiveandreactivepowerofactivedistributionnetworkbasedonsafetyreinforcementlearning