Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control

Battery energy storage systems (BESSs) are able to facilitate economical operation of the grid through demand response (DR), and are regarded as the most significant DR resource. Among them, distributed BESS integrating home photovoltaics (PV) have developed rapidly, and account for nearly 40% of ne...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wenying Li, Ming Tang, Xinzhen Zhang, Danhui Gao, Jian Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	grid edge control demand response (DR) deep reinforcement learning (DRL) multi-agent algorithm distributed battery energy storage system (BESS) three-phase unbalance Technology T
Acceso en línea:	https://doaj.org/article/445e25fbd8364979ad3639d27eb2c7de
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:445e25fbd8364979ad3639d27eb2c7de
record_format	dspace
spelling	oai:doaj.org-article:445e25fbd8364979ad3639d27eb2c7de2021-11-25T17:28:26ZOperation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control10.3390/en142277491996-1073https://doaj.org/article/445e25fbd8364979ad3639d27eb2c7de2021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/22/7749https://doaj.org/toc/1996-1073Battery energy storage systems (BESSs) are able to facilitate economical operation of the grid through demand response (DR), and are regarded as the most significant DR resource. Among them, distributed BESS integrating home photovoltaics (PV) have developed rapidly, and account for nearly 40% of newly installed capacity. However, the use scenarios and use efficiency of distributed BESS are far from sufficient to be able to utilize the potential loads and overcome uncertainties caused by disorderly operation. In this paper, the low-voltage transformer-powered area (LVTPA) is firstly defined, and then a DR grid edge controller was implemented based on deep reinforcement learning to maximize the total DR benefits and promote three-phase balance in the LVTPA. The proposed DR problem is formulated as a Markov decision process (MDP). In addition, the deep deterministic policy gradient (DDPG) algorithm is applied to train the controller in order to learn the optimal DR strategy. Additionally, a life cycle cost model of the BESS is established and implemented in the DR scheme to measure the income. The numerical results, compared to deep Q learning and model-based methods, demonstrate the effectiveness and validity of the proposed method.Wenying LiMing TangXinzhen ZhangDanhui GaoJian WangMDPI AGarticlegrid edge controldemand response (DR)deep reinforcement learning (DRL)multi-agent algorithmdistributed battery energy storage system (BESS)three-phase unbalanceTechnologyTENEnergies, Vol 14, Iss 7749, p 7749 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	grid edge control demand response (DR) deep reinforcement learning (DRL) multi-agent algorithm distributed battery energy storage system (BESS) three-phase unbalance Technology T
spellingShingle	grid edge control demand response (DR) deep reinforcement learning (DRL) multi-agent algorithm distributed battery energy storage system (BESS) three-phase unbalance Technology T Wenying Li Ming Tang Xinzhen Zhang Danhui Gao Jian Wang Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control
description	Battery energy storage systems (BESSs) are able to facilitate economical operation of the grid through demand response (DR), and are regarded as the most significant DR resource. Among them, distributed BESS integrating home photovoltaics (PV) have developed rapidly, and account for nearly 40% of newly installed capacity. However, the use scenarios and use efficiency of distributed BESS are far from sufficient to be able to utilize the potential loads and overcome uncertainties caused by disorderly operation. In this paper, the low-voltage transformer-powered area (LVTPA) is firstly defined, and then a DR grid edge controller was implemented based on deep reinforcement learning to maximize the total DR benefits and promote three-phase balance in the LVTPA. The proposed DR problem is formulated as a Markov decision process (MDP). In addition, the deep deterministic policy gradient (DDPG) algorithm is applied to train the controller in order to learn the optimal DR strategy. Additionally, a life cycle cost model of the BESS is established and implemented in the DR scheme to measure the income. The numerical results, compared to deep Q learning and model-based methods, demonstrate the effectiveness and validity of the proposed method.
format	article
author	Wenying Li Ming Tang Xinzhen Zhang Danhui Gao Jian Wang
author_facet	Wenying Li Ming Tang Xinzhen Zhang Danhui Gao Jian Wang
author_sort	Wenying Li
title	Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control
title_short	Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control
title_full	Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control
title_fullStr	Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control
title_full_unstemmed	Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control
title_sort	operation of distributed battery considering demand response using deep reinforcement learning in grid edge control
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/445e25fbd8364979ad3639d27eb2c7de
work_keys_str_mv	AT wenyingli operationofdistributedbatteryconsideringdemandresponseusingdeepreinforcementlearningingridedgecontrol AT mingtang operationofdistributedbatteryconsideringdemandresponseusingdeepreinforcementlearningingridedgecontrol AT xinzhenzhang operationofdistributedbatteryconsideringdemandresponseusingdeepreinforcementlearningingridedgecontrol AT danhuigao operationofdistributedbatteryconsideringdemandresponseusingdeepreinforcementlearningingridedgecontrol AT jianwang operationofdistributedbatteryconsideringdemandresponseusingdeepreinforcementlearningingridedgecontrol
_version_	1718412280985550848

Operation of Distributed Battery Considering Demand Response Using Deep Reinforcement Learning in Grid Edge Control

Ejemplares similares