Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid

Jaemin Park; Taehyeon Kwon; Bongseok Kim; Yujeong Hwang; Min Kyu Sim

doi:10.1109/GlobConHT56829.2023.10087384

Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid

Jaemin Park
, Taehyeon Kwon
, Bongseok Kim
, Yujeong Hwang
, Min Kyu Sim

Dept. of Industrial Engineering

Seoul National University of Science and Technology (SNUST)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The increasing utilization of renewable energy sources, such as photovoltaic (PV) power, has led to a growing interest in managing surplus PV power in order to generate additional profits. In particular, the use of energy storage systems (ESS) for handling surplus PV power has gained significant attention due to their ability to control the unstable and erratic nature of solar power systems. This paper presents an optimal ESS control scheme based on multi-agent reinforcement learning (MARL) that maximizes grid benefits. The proposed method is evaluated in a grid environment that includes a central ESS, multiple PV power prosumers, and consumers. The results of our empirical study demonstrate that the proposed method generates an additional profit of 18% to 36% compared to the current method used by Korean power providers for calculating prosumer profits. Furthermore, we discovered was found that as the proportion of prosumers in the total population increases, energy efficiency also increases proportionally.

Original language	English
Title of host publication	2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350332117
DOIs	https://doi.org/10.1109/GlobConHT56829.2023.10087384
State	Published - 2023
Event	2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023 - Male, Maldives Duration: 11 Mar 2023 → 12 Mar 2023

Publication series

Name	2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023

Conference

Conference	2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023
Country/Territory	Maldives
City	Male
Period	11/03/23 → 12/03/23

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Demand Response
Energy management
Energy Storage Systems (ESS)
Multi-Agent Reinforcement Learning
Photovoltaic (PV)
Smart Grid

Access to Document

10.1109/GlobConHT56829.2023.10087384

Cite this

Park, J., Kwon, T., Kim, B., Hwang, Y., & Sim, M. K. (2023). Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid. In 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023 (2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobConHT56829.2023.10087384

Park, Jaemin ; Kwon, Taehyeon ; Kim, Bongseok et al. / Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid. 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023).

@inproceedings{b4f7393b2e8a4a5090306ec0289201a8,

title = "Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid",

abstract = "The increasing utilization of renewable energy sources, such as photovoltaic (PV) power, has led to a growing interest in managing surplus PV power in order to generate additional profits. In particular, the use of energy storage systems (ESS) for handling surplus PV power has gained significant attention due to their ability to control the unstable and erratic nature of solar power systems. This paper presents an optimal ESS control scheme based on multi-agent reinforcement learning (MARL) that maximizes grid benefits. The proposed method is evaluated in a grid environment that includes a central ESS, multiple PV power prosumers, and consumers. The results of our empirical study demonstrate that the proposed method generates an additional profit of 18\% to 36\% compared to the current method used by Korean power providers for calculating prosumer profits. Furthermore, we discovered was found that as the proportion of prosumers in the total population increases, energy efficiency also increases proportionally.",

keywords = "Demand Response, Energy management, Energy Storage Systems (ESS), Multi-Agent Reinforcement Learning, Photovoltaic (PV), Smart Grid",

author = "Jaemin Park and Taehyeon Kwon and Bongseok Kim and Yujeong Hwang and Sim, \{Min Kyu\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023 ; Conference date: 11-03-2023 Through 12-03-2023",

year = "2023",

doi = "10.1109/GlobConHT56829.2023.10087384",

language = "English",

series = "2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023",

}

Park, J, Kwon, T, Kim, B, Hwang, Y & Sim, MK 2023, Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid. in 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023. 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023, Male, Maldives, 11/03/23. https://doi.org/10.1109/GlobConHT56829.2023.10087384

Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid. / Park, Jaemin; Kwon, Taehyeon; Kim, Bongseok et al.
2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid

AU - Park, Jaemin

AU - Kwon, Taehyeon

AU - Kim, Bongseok

AU - Hwang, Yujeong

AU - Sim, Min Kyu

PY - 2023

Y1 - 2023

N2 - The increasing utilization of renewable energy sources, such as photovoltaic (PV) power, has led to a growing interest in managing surplus PV power in order to generate additional profits. In particular, the use of energy storage systems (ESS) for handling surplus PV power has gained significant attention due to their ability to control the unstable and erratic nature of solar power systems. This paper presents an optimal ESS control scheme based on multi-agent reinforcement learning (MARL) that maximizes grid benefits. The proposed method is evaluated in a grid environment that includes a central ESS, multiple PV power prosumers, and consumers. The results of our empirical study demonstrate that the proposed method generates an additional profit of 18% to 36% compared to the current method used by Korean power providers for calculating prosumer profits. Furthermore, we discovered was found that as the proportion of prosumers in the total population increases, energy efficiency also increases proportionally.

AB - The increasing utilization of renewable energy sources, such as photovoltaic (PV) power, has led to a growing interest in managing surplus PV power in order to generate additional profits. In particular, the use of energy storage systems (ESS) for handling surplus PV power has gained significant attention due to their ability to control the unstable and erratic nature of solar power systems. This paper presents an optimal ESS control scheme based on multi-agent reinforcement learning (MARL) that maximizes grid benefits. The proposed method is evaluated in a grid environment that includes a central ESS, multiple PV power prosumers, and consumers. The results of our empirical study demonstrate that the proposed method generates an additional profit of 18% to 36% compared to the current method used by Korean power providers for calculating prosumer profits. Furthermore, we discovered was found that as the proportion of prosumers in the total population increases, energy efficiency also increases proportionally.

KW - Demand Response

KW - Energy management

KW - Energy Storage Systems (ESS)

KW - Multi-Agent Reinforcement Learning

KW - Photovoltaic (PV)

KW - Smart Grid

UR - https://www.scopus.com/pages/publications/85153571790

U2 - 10.1109/GlobConHT56829.2023.10087384

DO - 10.1109/GlobConHT56829.2023.10087384

M3 - Conference contribution

AN - SCOPUS:85153571790

T3 - 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023

BT - 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023

Y2 - 11 March 2023 through 12 March 2023

ER -

Park J, Kwon T, Kim B, Hwang Y, Sim MK. Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid. In 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies, GlobConHT 2023). doi: 10.1109/GlobConHT56829.2023.10087384

Multi-Agent Reinforcement Learning Based Optimal PV-ESS Control in Grid

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this