A Learning-Based Bidding Approach for PV-Attached BESS Power Plants

Xiang Gao; Haomin Ma; Ka Wing Chan; Shiwei Xia; Ziqing Zhu

doi:10.3389/fenrg.2021.750796

A Learning-Based Bidding Approach for PV-Attached BESS Power Plants

Xiang Gao, Haomin Ma, Ka Wing Chan, Shiwei Xia, Ziqing Zhu

The Hong Kong Polytechnic University

Research output: Journal article publication › Journal article › Academic research › peer-review

2 Citations (Scopus)

Abstract

Large-scale renewable photovoltaic (PV) and battery energy storage system (BESS) units are promising to be significant electricity suppliers in the future electricity market. A bidding model is proposed for PV-integrated BESS power plants in a pool-based day-ahead (DA) electricity market, in which the uncertainty of PV generation output is considered. In the proposed model, we consider the market clearing process as the external environment, while each agent updates the bid price through the communication with the market environment for its revenue maximization. A multiagent reinforcement learning (MARL) called win-or-learn-fast policy-hill-climbing (WoLF-PHC) is used to explore optimal bid prices without any information of opponents. The case study validates the computational performance of WoLF-PHC in the proposed model, while the bidding strategy of each participated agent is thereafter analyzed.

Original language	English
Article number	750796
Pages (from-to)	1-9
Number of pages	9
Journal	Frontiers in Energy Research
Volume	9
DOIs	https://doi.org/10.3389/fenrg.2021.750796
Publication status	Published - 11 Oct 2021

Keywords

BESS
bidding strategy
incomplete information game
multiagent reinforcement learning
PV
WoLF-PHC

ASJC Scopus subject areas

Renewable Energy, Sustainability and the Environment
Fuel Technology
Energy Engineering and Power Technology
Economics and Econometrics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

More information

10.3389/fenrg.2021.750796

http://hdl.handle.net/10397/97701

Cite this

@article{ba8437a55caf4d329d1c0b3ddfdec738,

title = "A Learning-Based Bidding Approach for PV-Attached BESS Power Plants",

abstract = "Large-scale renewable photovoltaic (PV) and battery energy storage system (BESS) units are promising to be significant electricity suppliers in the future electricity market. A bidding model is proposed for PV-integrated BESS power plants in a pool-based day-ahead (DA) electricity market, in which the uncertainty of PV generation output is considered. In the proposed model, we consider the market clearing process as the external environment, while each agent updates the bid price through the communication with the market environment for its revenue maximization. A multiagent reinforcement learning (MARL) called win-or-learn-fast policy-hill-climbing (WoLF-PHC) is used to explore optimal bid prices without any information of opponents. The case study validates the computational performance of WoLF-PHC in the proposed model, while the bidding strategy of each participated agent is thereafter analyzed.",

keywords = "BESS, bidding strategy, incomplete information game, multiagent reinforcement learning, PV, WoLF-PHC",

author = "Xiang Gao and Haomin Ma and Chan, {Ka Wing} and Shiwei Xia and Ziqing Zhu",

note = "Funding Information: This work was jointly supported by the Shenzhen Polytechnic, the Hong Kong Polytechnic University, the Natural Science Foundation of Guangdong Province, 2020A1515010461, the National Natural Science Foundation of China (52077075), and the Jiangsu Basic Research Project (BK20180284). Publisher Copyright: {\textcopyright} Copyright {\textcopyright} 2021 Gao, Ma, Chan, Xia and Zhu.",

year = "2021",

month = oct,

day = "11",

doi = "10.3389/fenrg.2021.750796",

language = "English",

volume = "9",

pages = "1--9",

journal = "Frontiers in Energy Research",

issn = "2296-598X",

publisher = "Frontiers Media SA",

}

TY - JOUR

T1 - A Learning-Based Bidding Approach for PV-Attached BESS Power Plants

AU - Gao, Xiang

AU - Ma, Haomin

AU - Chan, Ka Wing

AU - Xia, Shiwei

AU - Zhu, Ziqing

N1 - Funding Information: This work was jointly supported by the Shenzhen Polytechnic, the Hong Kong Polytechnic University, the Natural Science Foundation of Guangdong Province, 2020A1515010461, the National Natural Science Foundation of China (52077075), and the Jiangsu Basic Research Project (BK20180284). Publisher Copyright: © Copyright © 2021 Gao, Ma, Chan, Xia and Zhu.

PY - 2021/10/11

Y1 - 2021/10/11

N2 - Large-scale renewable photovoltaic (PV) and battery energy storage system (BESS) units are promising to be significant electricity suppliers in the future electricity market. A bidding model is proposed for PV-integrated BESS power plants in a pool-based day-ahead (DA) electricity market, in which the uncertainty of PV generation output is considered. In the proposed model, we consider the market clearing process as the external environment, while each agent updates the bid price through the communication with the market environment for its revenue maximization. A multiagent reinforcement learning (MARL) called win-or-learn-fast policy-hill-climbing (WoLF-PHC) is used to explore optimal bid prices without any information of opponents. The case study validates the computational performance of WoLF-PHC in the proposed model, while the bidding strategy of each participated agent is thereafter analyzed.

AB - Large-scale renewable photovoltaic (PV) and battery energy storage system (BESS) units are promising to be significant electricity suppliers in the future electricity market. A bidding model is proposed for PV-integrated BESS power plants in a pool-based day-ahead (DA) electricity market, in which the uncertainty of PV generation output is considered. In the proposed model, we consider the market clearing process as the external environment, while each agent updates the bid price through the communication with the market environment for its revenue maximization. A multiagent reinforcement learning (MARL) called win-or-learn-fast policy-hill-climbing (WoLF-PHC) is used to explore optimal bid prices without any information of opponents. The case study validates the computational performance of WoLF-PHC in the proposed model, while the bidding strategy of each participated agent is thereafter analyzed.

KW - BESS

KW - bidding strategy

KW - incomplete information game

KW - multiagent reinforcement learning

KW - PV

KW - WoLF-PHC

UR - http://www.scopus.com/inward/record.url?scp=85117696028&partnerID=8YFLogxK

U2 - 10.3389/fenrg.2021.750796

DO - 10.3389/fenrg.2021.750796

M3 - Journal article

AN - SCOPUS:85117696028

SN - 2296-598X

VL - 9

SP - 1

EP - 9

JO - Frontiers in Energy Research

JF - Frontiers in Energy Research

M1 - 750796

ER -

A Learning-Based Bidding Approach for PV-Attached BESS Power Plants

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

More information

Other files and links

Fingerprint

Cite this