Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input

Shih Wen Lin; Chia Chi Chu

doi:10.1109/ICPS57144.2023.10142088

Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input

Shih Wen Lin, Chia Chi Chu

National Tsing Hua University

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

1 Scopus citations

Abstract

A model-free data-driven Q-learning algorithm for distributed control in isolated AC MGs is proposed for achieving the autonomous voltage restoration. First, by using the feedback linearization technique to each DG, a second-order linear system is defined. Then the distributed voltage restoration problem is re-formulated a consensus problem. We study this consensus problem subject to saturated inputs. An iterative model-free datadriven Q-learning algorithm is adopted to achieve the voltage restoration. Simulation of an isolated micro-grids have performed to demonstrate the effectiveness of the proposed method.

Original language	English
Title of host publication	2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350396515
DOIs	https://doi.org/10.1109/ICPS57144.2023.10142088
State	Published - 2023
Externally published	Yes
Event	59th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2023 - Las Vegas, United States Duration: 21 05 2023 → 25 05 2023

Publication series

Name	Conference Record - Industrial and Commercial Power Systems Technical Conference
Volume	2023-May

Conference

Conference	59th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2023
Country/Territory	United States
City	Las Vegas
Period	21/05/23 → 25/05/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Microgrid
Q-learning
consensus control
distributed secondary voltage control
reinforcement learning
saturated limit

Access to Document

10.1109/ICPS57144.2023.10142088

Cite this

Lin, S. W., & Chu, C. C. (2023). Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input. In 2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023 (Conference Record - Industrial and Commercial Power Systems Technical Conference; Vol. 2023-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPS57144.2023.10142088

Lin, Shih Wen ; Chu, Chia Chi. / Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input. 2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Conference Record - Industrial and Commercial Power Systems Technical Conference).

@inproceedings{f664357ed55f4567a0f243588c9073e6,

title = "Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input",

abstract = "A model-free data-driven Q-learning algorithm for distributed control in isolated AC MGs is proposed for achieving the autonomous voltage restoration. First, by using the feedback linearization technique to each DG, a second-order linear system is defined. Then the distributed voltage restoration problem is re-formulated a consensus problem. We study this consensus problem subject to saturated inputs. An iterative model-free datadriven Q-learning algorithm is adopted to achieve the voltage restoration. Simulation of an isolated micro-grids have performed to demonstrate the effectiveness of the proposed method.",

keywords = "Microgrid, Q-learning, consensus control, distributed secondary voltage control, reinforcement learning, saturated limit",

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

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 59th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2023 ; Conference date: 21-05-2023 Through 25-05-2023",

year = "2023",

doi = "10.1109/ICPS57144.2023.10142088",

language = "英语",

series = "Conference Record - Industrial and Commercial Power Systems Technical Conference",

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

booktitle = "2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023",

address = "美国",

}

Lin, SW & Chu, CC 2023, Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input. in 2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023. Conference Record - Industrial and Commercial Power Systems Technical Conference, vol. 2023-May, Institute of Electrical and Electronics Engineers Inc., 59th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2023, Las Vegas, United States, 21/05/23. https://doi.org/10.1109/ICPS57144.2023.10142088

Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input. / Lin, Shih Wen; Chu, Chia Chi.
2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Conference Record - Industrial and Commercial Power Systems Technical Conference; Vol. 2023-May).

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

TY - GEN

T1 - Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input

AU - Lin, Shih Wen

AU - Chu, Chia Chi

PY - 2023

Y1 - 2023

N2 - A model-free data-driven Q-learning algorithm for distributed control in isolated AC MGs is proposed for achieving the autonomous voltage restoration. First, by using the feedback linearization technique to each DG, a second-order linear system is defined. Then the distributed voltage restoration problem is re-formulated a consensus problem. We study this consensus problem subject to saturated inputs. An iterative model-free datadriven Q-learning algorithm is adopted to achieve the voltage restoration. Simulation of an isolated micro-grids have performed to demonstrate the effectiveness of the proposed method.

AB - A model-free data-driven Q-learning algorithm for distributed control in isolated AC MGs is proposed for achieving the autonomous voltage restoration. First, by using the feedback linearization technique to each DG, a second-order linear system is defined. Then the distributed voltage restoration problem is re-formulated a consensus problem. We study this consensus problem subject to saturated inputs. An iterative model-free datadriven Q-learning algorithm is adopted to achieve the voltage restoration. Simulation of an isolated micro-grids have performed to demonstrate the effectiveness of the proposed method.

KW - Microgrid

KW - Q-learning

KW - consensus control

KW - distributed secondary voltage control

KW - reinforcement learning

KW - saturated limit

UR - http://www.scopus.com/inward/record.url?scp=85162705310&partnerID=8YFLogxK

U2 - 10.1109/ICPS57144.2023.10142088

DO - 10.1109/ICPS57144.2023.10142088

M3 - 会议稿件

AN - SCOPUS:85162705310

T3 - Conference Record - Industrial and Commercial Power Systems Technical Conference

BT - 2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 59th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2023

Y2 - 21 May 2023 through 25 May 2023

ER -

Lin SW, Chu CC. Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input. In 2023 IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, I and CPS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (Conference Record - Industrial and Commercial Power Systems Technical Conference). doi: 10.1109/ICPS57144.2023.10142088

Distributed Q-Learning Secondary Voltage Control of Isolated AC Microgrids with Saturated Input

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this