Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids

Shih Wen Lin; Chia Chi Chu; Chien Feng Tung

doi:10.1109/IAS54023.2022.9939855

Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids

Shih Wen Lin, Chia Chi Chu, Chien Feng Tung

National Tsing Hua University

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

5 Scopus citations

Abstract

We consider frequency synchronization and voltage restoration of the isolated micro-grids (MG) by distributed reinforcement learning droop control methods. By exploring the data-driven Q-learning algorithm with the adjacent information sharing mechanism, a fully distributed model-free Q-learning-based droop control is adopted for autonomous frequency synchronization and voltage restoration. Since the proposed distributed control is indeed model-free, it is very suitable for plug-and-play operations of isolated MGs if sufficient operation data of MGs are well-collected. To validate the performance of the proposed method, the proposed distributed Q-learning algorithm was implemented on Matlab/Simulink environment. Simulation results of modified IEEE 34-node distribution system can demonstrate the effectiveness of the proposed distributed Q-learning droop control.

Original language	English
Title of host publication	2022 IEEE Industry Applications Society Annual Meeting, IAS 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665478151
DOIs	https://doi.org/10.1109/IAS54023.2022.9939855
State	Published - 2022
Externally published	Yes
Event	2022 IEEE Industry Applications Society Annual Meeting, IAS 2022 - Detroit, United States Duration: 09 10 2022 → 14 10 2022

Publication series

Name	Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)
Volume	2022-October
ISSN (Print)	0197-2618

Conference

Conference	2022 IEEE Industry Applications Society Annual Meeting, IAS 2022
Country/Territory	United States
City	Detroit
Period	09/10/22 → 14/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Access to Document

10.1109/IAS54023.2022.9939855

Cite this

Lin, S. W., Chu, C. C., & Tung, C. F. (2022). Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids. In 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022 (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society); Vol. 2022-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IAS54023.2022.9939855

Lin, Shih Wen ; Chu, Chia Chi ; Tung, Chien Feng. / Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids. 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)).

@inproceedings{926f45468f14485c93354b4f728c21b2,

title = "Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids",

abstract = "We consider frequency synchronization and voltage restoration of the isolated micro-grids (MG) by distributed reinforcement learning droop control methods. By exploring the data-driven Q-learning algorithm with the adjacent information sharing mechanism, a fully distributed model-free Q-learning-based droop control is adopted for autonomous frequency synchronization and voltage restoration. Since the proposed distributed control is indeed model-free, it is very suitable for plug-and-play operations of isolated MGs if sufficient operation data of MGs are well-collected. To validate the performance of the proposed method, the proposed distributed Q-learning algorithm was implemented on Matlab/Simulink environment. Simulation results of modified IEEE 34-node distribution system can demonstrate the effectiveness of the proposed distributed Q-learning droop control.",

author = "Lin, {Shih Wen} and Chu, {Chia Chi} and Tung, {Chien Feng}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022 ; Conference date: 09-10-2022 Through 14-10-2022",

year = "2022",

doi = "10.1109/IAS54023.2022.9939855",

language = "英语",

series = "Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)",

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

booktitle = "2022 IEEE Industry Applications Society Annual Meeting, IAS 2022",

address = "美国",

}

Lin, SW, Chu, CC & Tung, CF 2022, Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids. in 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022. Conference Record - IAS Annual Meeting (IEEE Industry Applications Society), vol. 2022-October, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022, Detroit, United States, 09/10/22. https://doi.org/10.1109/IAS54023.2022.9939855

Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids. / Lin, Shih Wen; Chu, Chia Chi; Tung, Chien Feng.
2022 IEEE Industry Applications Society Annual Meeting, IAS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society); Vol. 2022-October).

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

TY - GEN

T1 - Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids

AU - Lin, Shih Wen

AU - Chu, Chia Chi

AU - Tung, Chien Feng

PY - 2022

Y1 - 2022

N2 - We consider frequency synchronization and voltage restoration of the isolated micro-grids (MG) by distributed reinforcement learning droop control methods. By exploring the data-driven Q-learning algorithm with the adjacent information sharing mechanism, a fully distributed model-free Q-learning-based droop control is adopted for autonomous frequency synchronization and voltage restoration. Since the proposed distributed control is indeed model-free, it is very suitable for plug-and-play operations of isolated MGs if sufficient operation data of MGs are well-collected. To validate the performance of the proposed method, the proposed distributed Q-learning algorithm was implemented on Matlab/Simulink environment. Simulation results of modified IEEE 34-node distribution system can demonstrate the effectiveness of the proposed distributed Q-learning droop control.

AB - We consider frequency synchronization and voltage restoration of the isolated micro-grids (MG) by distributed reinforcement learning droop control methods. By exploring the data-driven Q-learning algorithm with the adjacent information sharing mechanism, a fully distributed model-free Q-learning-based droop control is adopted for autonomous frequency synchronization and voltage restoration. Since the proposed distributed control is indeed model-free, it is very suitable for plug-and-play operations of isolated MGs if sufficient operation data of MGs are well-collected. To validate the performance of the proposed method, the proposed distributed Q-learning algorithm was implemented on Matlab/Simulink environment. Simulation results of modified IEEE 34-node distribution system can demonstrate the effectiveness of the proposed distributed Q-learning droop control.

UR - http://www.scopus.com/inward/record.url?scp=85142808733&partnerID=8YFLogxK

U2 - 10.1109/IAS54023.2022.9939855

DO - 10.1109/IAS54023.2022.9939855

M3 - 会议稿件

AN - SCOPUS:85142808733

T3 - Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)

BT - 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022

Y2 - 9 October 2022 through 14 October 2022

ER -

Lin SW, Chu CC, Tung CF. Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids. In 2022 IEEE Industry Applications Society Annual Meeting, IAS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)). doi: 10.1109/IAS54023.2022.9939855

Distributed Q-Learning Droop Control for Frequency Synchronization and Voltage Restoration in Isolated AC Micro-Grids

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this