Deep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint Dispatch

A deep reinforcement learning based wind-photovoltaic-storage system joint dispatch model is proposed. First, a joint dispatch model that fully considers the constraints of various wind and solar storage stations is established, where tracking dispatch plans, wind and solar curtailment, and energy s...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuxing ZHANG, Chi MA, Zhixue YANG, Yao WANG, Hao WU, Zhouyang REN
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2023-02-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202107065
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031806715265024
author Shuxing ZHANG
Chi MA
Zhixue YANG
Yao WANG
Hao WU
Zhouyang REN
author_facet Shuxing ZHANG
Chi MA
Zhixue YANG
Yao WANG
Hao WU
Zhouyang REN
author_sort Shuxing ZHANG
collection DOAJ
description A deep reinforcement learning based wind-photovoltaic-storage system joint dispatch model is proposed. First, a joint dispatch model that fully considers the constraints of various wind and solar storage stations is established, where tracking dispatch plans, wind and solar curtailment, and energy storage operation costs are considered in the objective function. Then, the state variables, action variables and reward function under the reinforcement learning framework are defined. Later, a deep deterministic policy gradient algorithm is introduced, using its environmental interaction and strategy exploration mechanism to learn the joint scheduling strategy, so as to achieve the dispatch strategy tracking, reduce wind and solar abandonment, and reduce energy storage charging and discharging. Finally, the historical data of wind power, photovoltaic, and dispatch plan in a certain area of northwestern China are employed to train and analyze the model. The results of the case studies show that the proposed method can adapt well to the changes in the wind power and photovoltaic power in different periods, and the joint scheduling strategy can be obtained under given data of wind and photovoltaic.
format Article
id doaj-art-3f6cb4e5fa2d47139a3c84e500922893
institution DOAJ
issn 1004-9649
language zho
publishDate 2023-02-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-3f6cb4e5fa2d47139a3c84e5009228932025-08-20T02:58:51ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492023-02-01562687610.11930/j.issn.1004-9649.202107065zgdl-56-2-zhangshuxingDeep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint DispatchShuxing ZHANG0Chi MA1Zhixue YANG2Yao WANG3Hao WU4Zhouyang REN5China Nuclear Power Technology Research Institute Co., Ltd., Shenzhen 518000, ChinaCGN New Energy Holdings Co., Ltd., Beijing 100084, ChinaState Key Laboratory of Power Transmission Equipment & System Security and New Technology (Chongqing University), Chongqing 400044, ChinaChina Nuclear Power Technology Research Institute Co., Ltd., Shenzhen 518000, ChinaChina Nuclear Power Technology Research Institute Co., Ltd., Shenzhen 518000, ChinaState Key Laboratory of Power Transmission Equipment & System Security and New Technology (Chongqing University), Chongqing 400044, ChinaA deep reinforcement learning based wind-photovoltaic-storage system joint dispatch model is proposed. First, a joint dispatch model that fully considers the constraints of various wind and solar storage stations is established, where tracking dispatch plans, wind and solar curtailment, and energy storage operation costs are considered in the objective function. Then, the state variables, action variables and reward function under the reinforcement learning framework are defined. Later, a deep deterministic policy gradient algorithm is introduced, using its environmental interaction and strategy exploration mechanism to learn the joint scheduling strategy, so as to achieve the dispatch strategy tracking, reduce wind and solar abandonment, and reduce energy storage charging and discharging. Finally, the historical data of wind power, photovoltaic, and dispatch plan in a certain area of northwestern China are employed to train and analyze the model. The results of the case studies show that the proposed method can adapt well to the changes in the wind power and photovoltaic power in different periods, and the joint scheduling strategy can be obtained under given data of wind and photovoltaic.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202107065wind-photovoltaic-storage hybrid systemjoint scheduling strategyuncertaintydeep reinforcement learningdeep deterministic policy gradient algorithm
spellingShingle Shuxing ZHANG
Chi MA
Zhixue YANG
Yao WANG
Hao WU
Zhouyang REN
Deep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint Dispatch
Zhongguo dianli
wind-photovoltaic-storage hybrid system
joint scheduling strategy
uncertainty
deep reinforcement learning
deep deterministic policy gradient algorithm
title Deep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint Dispatch
title_full Deep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint Dispatch
title_fullStr Deep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint Dispatch
title_full_unstemmed Deep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint Dispatch
title_short Deep Deterministic Policy Gradient Algorithm Based Wind-Photovoltaic-Storage Hybrid System Joint Dispatch
title_sort deep deterministic policy gradient algorithm based wind photovoltaic storage hybrid system joint dispatch
topic wind-photovoltaic-storage hybrid system
joint scheduling strategy
uncertainty
deep reinforcement learning
deep deterministic policy gradient algorithm
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202107065
work_keys_str_mv AT shuxingzhang deepdeterministicpolicygradientalgorithmbasedwindphotovoltaicstoragehybridsystemjointdispatch
AT chima deepdeterministicpolicygradientalgorithmbasedwindphotovoltaicstoragehybridsystemjointdispatch
AT zhixueyang deepdeterministicpolicygradientalgorithmbasedwindphotovoltaicstoragehybridsystemjointdispatch
AT yaowang deepdeterministicpolicygradientalgorithmbasedwindphotovoltaicstoragehybridsystemjointdispatch
AT haowu deepdeterministicpolicygradientalgorithmbasedwindphotovoltaicstoragehybridsystemjointdispatch
AT zhouyangren deepdeterministicpolicygradientalgorithmbasedwindphotovoltaicstoragehybridsystemjointdispatch