Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning

Yoon Gun Jung; Minhyeok Chang; Sungwoo Kang; Gilsoo Jang; Hojun Lee; Minhan Yoon; Sungyoon Song; Changhee Han

doi:10.1109/PESGM52003.2023.10253225

Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning

Yoon Gun Jung^*
, Minhyeok Chang
, Sungwoo Kang
, Gilsoo Jang
, Hojun Lee
, Minhan Yoon
, Sungyoon Song
, Changhee Han

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation.

Original language	English
Title of host publication	2023 IEEE Power and Energy Society General Meeting, PESGM 2023
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665464413
DOIs	https://doi.org/10.1109/PESGM52003.2023.10253225
Publication status	Published - 2023
Event	2023 IEEE Power and Energy Society General Meeting, PESGM 2023 - Orlando, United States Duration: 2023 Jul 16 → 2023 Jul 20

Publication series

Name	IEEE Power and Energy Society General Meeting
Volume	2023-July
ISSN (Print)	1944-9925
ISSN (Electronic)	1944-9933

Conference

Conference	2023 IEEE Power and Energy Society General Meeting, PESGM 2023
Country/Territory	United States
City	Orlando
Period	23/7/16 → 23/7/20

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Deep Reinforcement Learning (DRL)
Distributed generation (DG)
Dynamic Multi-Microgrid Formulation
Microgrid (MG)
Reconfiguration
Spanning Tree Algorithm

ASJC Scopus subject areas

Energy Engineering and Power Technology
Nuclear Energy and Engineering
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering

Access to Document

10.1109/PESGM52003.2023.10253225

Cite this

Jung, Y. G., Chang, M., Kang, S., Jang, G., Lee, H., Yoon, M., Song, S., & Han, C. (2023). Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning. In 2023 IEEE Power and Energy Society General Meeting, PESGM 2023 (IEEE Power and Energy Society General Meeting; Vol. 2023-July). IEEE Computer Society. https://doi.org/10.1109/PESGM52003.2023.10253225

Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning. / Jung, Yoon Gun; Chang, Minhyeok; Kang, Sungwoo et al.
2023 IEEE Power and Energy Society General Meeting, PESGM 2023. IEEE Computer Society, 2023. (IEEE Power and Energy Society General Meeting; Vol. 2023-July).

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

Jung, YG, Chang, M, Kang, S, Jang, G, Lee, H, Yoon, M, Song, S & Han, C 2023, Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning. in 2023 IEEE Power and Energy Society General Meeting, PESGM 2023. IEEE Power and Energy Society General Meeting, vol. 2023-July, IEEE Computer Society, 2023 IEEE Power and Energy Society General Meeting, PESGM 2023, Orlando, United States, 23/7/16. https://doi.org/10.1109/PESGM52003.2023.10253225

@inproceedings{16090bbca49b4017b1ab8a7547cce437,

title = "Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning",

abstract = "This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation.",

keywords = "Deep Reinforcement Learning (DRL), Distributed generation (DG), Dynamic Multi-Microgrid Formulation, Microgrid (MG), Reconfiguration, Spanning Tree Algorithm",

author = "Jung, \{Yoon Gun\} and Minhyeok Chang and Sungwoo Kang and Gilsoo Jang and Hojun Lee and Minhan Yoon and Sungyoon Song and Changhee Han",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Power and Energy Society General Meeting, PESGM 2023 ; Conference date: 16-07-2023 Through 20-07-2023",

year = "2023",

doi = "10.1109/PESGM52003.2023.10253225",

language = "English",

series = "IEEE Power and Energy Society General Meeting",

publisher = "IEEE Computer Society",

booktitle = "2023 IEEE Power and Energy Society General Meeting, PESGM 2023",

}

TY - GEN

T1 - Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning

AU - Jung, Yoon Gun

AU - Chang, Minhyeok

AU - Kang, Sungwoo

AU - Jang, Gilsoo

AU - Lee, Hojun

AU - Yoon, Minhan

AU - Song, Sungyoon

AU - Han, Changhee

PY - 2023

Y1 - 2023

N2 - This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation.

AB - This paper proposes an online Dynamic Multi-Microgrid Formulation (DMMF) method using Deep Reinforcement Learning. It aims to reconfigure the microgrid into several self-supplied islands and minimize total operation cost at the same time. Spanning Tree Algorithm is used to reduce the total number of microgrid formulation. Proximal-Policy optimization is implemented to train the agent which determines the status of sectionalizing switches in microgrid in real-time. To show the effectiveness of the proposed DMMF method, a case study was conducted in the modified cigre-14 bus test network. The results demonstrated that the proposed DMMF method reduced the total operation cost compared to the operation cost derive from original Cigre 14 bus formulation.

KW - Deep Reinforcement Learning (DRL)

KW - Distributed generation (DG)

KW - Dynamic Multi-Microgrid Formulation

KW - Microgrid (MG)

KW - Reconfiguration

KW - Spanning Tree Algorithm

UR - https://www.scopus.com/pages/publications/85174719867

U2 - 10.1109/PESGM52003.2023.10253225

DO - 10.1109/PESGM52003.2023.10253225

M3 - Conference contribution

AN - SCOPUS:85174719867

T3 - IEEE Power and Energy Society General Meeting

BT - 2023 IEEE Power and Energy Society General Meeting, PESGM 2023

PB - IEEE Computer Society

T2 - 2023 IEEE Power and Energy Society General Meeting, PESGM 2023

Y2 - 16 July 2023 through 20 July 2023

ER -

Cost Effective Dynamic Multi-Microgrid Formulation Method Using Deep Reinforcement Learning

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this