A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control

Guanyu Zhang; Mengjie Teng; Chen Chen; Zhaohong Bie

doi:10.1109/ICPSAsia55496.2022.9949649

A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control

Guanyu Zhang
, Mengjie Teng
, Chen Chen
, Zhaohong Bie

电气工程学院

Xi'an Jiaotong University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

16 引用（Scopus）

摘要

With the increasing penetration of renewable energy and power electronic devices, the frequency fluctuation of the power system will increase sharply, the inertia will decrease significantly, the damping characteristics will be poor, and the frequency adjustment ability needs to be improved. In this paper, a DRL (deep reinforcement learning) based framework is propsed to solve the LFC (load frequency control) problem for power system. This paper first introduces the model of LFC and basic description of DRL. Then the flow of twin delayed deep deterministic policy gradient (TD3) algorithm and a general framework for load frequency control. Finally, the proposed method is verified through a single area LFC test system. The implementation demonstrates that the proposed method is effective in LFC problem.

源语言	英语
主期刊名	I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia
出版商	Institute of Electrical and Electronics Engineers Inc.
页	1801-1805
页数	5
ISBN（电子版）	9781665450669
DOI	https://doi.org/10.1109/ICPSAsia55496.2022.9949649
出版状态	已出版 - 2022
活动	2022 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2022 - Shanghai, 中国期限: 8 7月 2022 → 11 7月 2022

出版系列

姓名	I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia

会议

会议	2022 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2022
国家/地区	中国
市	Shanghai
时期	8/07/22 → 11/07/22

联合国可持续发展目标

此成果有助于实现下列可持续发展目标：

可持续发展目标 7 经济适用的清洁能源

访问文件

10.1109/ICPSAsia55496.2022.9949649

其它文件与链接

链接到 Scopus 的出版物

引用此

Zhang, G., Teng, M., Chen, C., & Bie, Z. (2022). A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control. 在 I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia (页码 1801-1805). (I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPSAsia55496.2022.9949649

Zhang, Guanyu ; Teng, Mengjie ; Chen, Chen 等. / A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control. I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia. Institute of Electrical and Electronics Engineers Inc., 2022. 页码 1801-1805 (I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia).

@inproceedings{08c4ad5c81c8490d8de5c729728256cb,

title = "A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control",

abstract = "With the increasing penetration of renewable energy and power electronic devices, the frequency fluctuation of the power system will increase sharply, the inertia will decrease significantly, the damping characteristics will be poor, and the frequency adjustment ability needs to be improved. In this paper, a DRL (deep reinforcement learning) based framework is propsed to solve the LFC (load frequency control) problem for power system. This paper first introduces the model of LFC and basic description of DRL. Then the flow of twin delayed deep deterministic policy gradient (TD3) algorithm and a general framework for load frequency control. Finally, the proposed method is verified through a single area LFC test system. The implementation demonstrates that the proposed method is effective in LFC problem.",

keywords = "artifical intelligence, deep reinforcement learning, load frequency control, power system frequency",

author = "Guanyu Zhang and Mengjie Teng and Chen Chen and Zhaohong Bie",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2022 ; Conference date: 08-07-2022 Through 11-07-2022",

year = "2022",

doi = "10.1109/ICPSAsia55496.2022.9949649",

language = "英语",

series = "I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia",

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

pages = "1801--1805",

booktitle = "I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia",

}

Zhang, G, Teng, M, Chen, C & Bie, Z 2022, A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control. 在 I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia. I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia, Institute of Electrical and Electronics Engineers Inc., 页码 1801-1805, 2022 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2022, Shanghai, 中国, 8/07/22. https://doi.org/10.1109/ICPSAsia55496.2022.9949649

A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control. / Zhang, Guanyu; Teng, Mengjie; Chen, Chen 等.
I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia. Institute of Electrical and Electronics Engineers Inc., 2022. 页码 1801-1805 (I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control

AU - Zhang, Guanyu

AU - Teng, Mengjie

AU - Chen, Chen

AU - Bie, Zhaohong

PY - 2022

Y1 - 2022

N2 - With the increasing penetration of renewable energy and power electronic devices, the frequency fluctuation of the power system will increase sharply, the inertia will decrease significantly, the damping characteristics will be poor, and the frequency adjustment ability needs to be improved. In this paper, a DRL (deep reinforcement learning) based framework is propsed to solve the LFC (load frequency control) problem for power system. This paper first introduces the model of LFC and basic description of DRL. Then the flow of twin delayed deep deterministic policy gradient (TD3) algorithm and a general framework for load frequency control. Finally, the proposed method is verified through a single area LFC test system. The implementation demonstrates that the proposed method is effective in LFC problem.

AB - With the increasing penetration of renewable energy and power electronic devices, the frequency fluctuation of the power system will increase sharply, the inertia will decrease significantly, the damping characteristics will be poor, and the frequency adjustment ability needs to be improved. In this paper, a DRL (deep reinforcement learning) based framework is propsed to solve the LFC (load frequency control) problem for power system. This paper first introduces the model of LFC and basic description of DRL. Then the flow of twin delayed deep deterministic policy gradient (TD3) algorithm and a general framework for load frequency control. Finally, the proposed method is verified through a single area LFC test system. The implementation demonstrates that the proposed method is effective in LFC problem.

KW - artifical intelligence

KW - deep reinforcement learning

KW - load frequency control

KW - power system frequency

UR - https://www.scopus.com/pages/publications/85143394594

U2 - 10.1109/ICPSAsia55496.2022.9949649

DO - 10.1109/ICPSAsia55496.2022.9949649

M3 - 会议稿件

AN - SCOPUS:85143394594

T3 - I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia

SP - 1801

EP - 1805

BT - I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2022

Y2 - 8 July 2022 through 11 July 2022

ER -

Zhang G, Teng M, Chen C , Bie Z. A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control. 在 I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia. Institute of Electrical and Electronics Engineers Inc. 2022. 页码 1801-1805. (I and CPS Asia 2022 - 2022 IEEE IAS Industrial and Commercial Power System Asia). doi: 10.1109/ICPSAsia55496.2022.9949649

A Deep Reinforcement Learning Based Framework for Power System Load Frequency Control

摘要

出版系列

会议

联合国可持续发展目标

访问文件

其它文件与链接

学术指纹

引用此