Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy
To achieve frequency stability and economic efficiency in isolated microgrids, grid operators face a trade-off between multiple performance indicators. This paper introduces a data-driven adaptive load frequency control (DD-ALFC) approach, where the load frequency controller is modeled as an agent t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2024.1361869/full |
| _version_ | 1827304566648995840 |
|---|---|
| author | Wanlin Du Xiangmin Huang Yuanzhe Zhu Ling Wang Wenyang Deng |
| author_facet | Wanlin Du Xiangmin Huang Yuanzhe Zhu Ling Wang Wenyang Deng |
| author_sort | Wanlin Du |
| collection | DOAJ |
| description | To achieve frequency stability and economic efficiency in isolated microgrids, grid operators face a trade-off between multiple performance indicators. This paper introduces a data-driven adaptive load frequency control (DD-ALFC) approach, where the load frequency controller is modeled as an agent that can balance different objectives autonomously. The paper also proposes a priority replay soft actor critic (PR-SAC) algorithm to implement the DD-ALFC method. The PR-SAC algorithm enhances the policy randomness by using entropy regularization and maximization, and improves the learning adaptability and generalization by using priority experience replay. The proposed DD-ALFC method based on the PR-SAC algorithm can achieve higher adaptability and robustness in complex microgrid environments with multiple performance indicators, and improve both the frequency control and the economic efficiency. The paper validates the effectiveness of the proposed method in the Zhuzhou Island microgrid. |
| first_indexed | 2024-04-24T17:39:06Z |
| format | Article |
| id | doaj.art-f9123e05ae2342548fd4af8336a9d757 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-24T17:39:06Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-f9123e05ae2342548fd4af8336a9d7572024-03-28T04:23:18ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2024-03-011210.3389/fenrg.2024.13618691361869Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economyWanlin Du0Xiangmin Huang1Yuanzhe Zhu2Ling Wang3Wenyang Deng4Guangdong Provincial Key Laboratory of Electric Power Equipment Reliability, Electric Power Research Institute of Guangdong Power Grid Co., Ltd., Guangzhou, Guangdong, ChinaCollege of Electric Power, South China University of Technology, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Electric Power Equipment Reliability, Electric Power Research Institute of Guangdong Power Grid Co., Ltd., Guangzhou, Guangdong, ChinaGuangdong Provincial Key Laboratory of Electric Power Equipment Reliability, Electric Power Research Institute of Guangdong Power Grid Co., Ltd., Guangzhou, Guangdong, ChinaCollege of Electric Power, South China University of Technology, Guangzhou, ChinaTo achieve frequency stability and economic efficiency in isolated microgrids, grid operators face a trade-off between multiple performance indicators. This paper introduces a data-driven adaptive load frequency control (DD-ALFC) approach, where the load frequency controller is modeled as an agent that can balance different objectives autonomously. The paper also proposes a priority replay soft actor critic (PR-SAC) algorithm to implement the DD-ALFC method. The PR-SAC algorithm enhances the policy randomness by using entropy regularization and maximization, and improves the learning adaptability and generalization by using priority experience replay. The proposed DD-ALFC method based on the PR-SAC algorithm can achieve higher adaptability and robustness in complex microgrid environments with multiple performance indicators, and improve both the frequency control and the economic efficiency. The paper validates the effectiveness of the proposed method in the Zhuzhou Island microgrid.https://www.frontiersin.org/articles/10.3389/fenrg.2024.1361869/fullload frequency controlisland microgridfrequency stabilitypriority replay soft actor criticdata-driven |
| spellingShingle | Wanlin Du Xiangmin Huang Yuanzhe Zhu Ling Wang Wenyang Deng Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy Frontiers in Energy Research load frequency control island microgrid frequency stability priority replay soft actor critic data-driven |
| title | Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy |
| title_full | Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy |
| title_fullStr | Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy |
| title_full_unstemmed | Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy |
| title_short | Deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy |
| title_sort | deep reinforcement learning for adaptive frequency control of island microgrid considering control performance and economy |
| topic | load frequency control island microgrid frequency stability priority replay soft actor critic data-driven |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2024.1361869/full |
| work_keys_str_mv | AT wanlindu deepreinforcementlearningforadaptivefrequencycontrolofislandmicrogridconsideringcontrolperformanceandeconomy AT xiangminhuang deepreinforcementlearningforadaptivefrequencycontrolofislandmicrogridconsideringcontrolperformanceandeconomy AT yuanzhezhu deepreinforcementlearningforadaptivefrequencycontrolofislandmicrogridconsideringcontrolperformanceandeconomy AT lingwang deepreinforcementlearningforadaptivefrequencycontrolofislandmicrogridconsideringcontrolperformanceandeconomy AT wenyangdeng deepreinforcementlearningforadaptivefrequencycontrolofislandmicrogridconsideringcontrolperformanceandeconomy |