Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning Algorithm
To address the issue of economic dispatch imbalance in virtual power plant (VPP) systems caused by the influence of operators and distribution networks, this study introduces an optimized economic dispatch method based on bi-level game theory. Firstly, a bi-level game model is formulated, which inte...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/18/2/374 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588553655156736 |
|---|---|
| author | Zhu Liu Guowei Guo Dehuang Gong Lingfeng Xuan Feiwu He Xinglin Wan Dongguo Zhou |
| author_facet | Zhu Liu Guowei Guo Dehuang Gong Lingfeng Xuan Feiwu He Xinglin Wan Dongguo Zhou |
| author_sort | Zhu Liu |
| collection | DOAJ |
| description | To address the issue of economic dispatch imbalance in virtual power plant (VPP) systems caused by the influence of operators and distribution networks, this study introduces an optimized economic dispatch method based on bi-level game theory. Firstly, a bi-level game model is formulated, which integrates the operational and environmental expenses of VPPs with the revenues of system operators. To avoid local optima during the search process, an enhanced reinforcement learning algorithm is developed to achieve rapid convergence and obtain the optimal solution. Finally, case analyses illustrate that the proposed method effectively accomplishes multi-objective optimization for various decision-making stakeholders, including VPP and system operators, while significantly reducing curtailment costs associated with the extensive integration of distributed renewable energy. Furthermore, the proposed algorithm achieves fast iteration and yields superior dispatch outcomes under the same modeling conditions. |
| format | Article |
| id | doaj-art-5f4fdf20895e4bc982aebb1224690365 |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-5f4fdf20895e4bc982aebb12246903652025-01-24T13:31:15ZengMDPI AGEnergies1996-10732025-01-0118237410.3390/en18020374Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning AlgorithmZhu Liu0Guowei Guo1Dehuang Gong2Lingfeng Xuan3Feiwu He4Xinglin Wan5Dongguo Zhou6China Southern Power Grid Research Technology Co., Ltd., Guangzhou 510663, ChinaGuangdong Electric Power Co., Ltd., Foshan Power Supply Bureau, Foshan 528061, ChinaGuangdong Electric Power Co., Ltd., Qingyuan Yingde Power Supply Bureau, Yingde 513099, ChinaGuangdong Electric Power Co., Ltd., Qingyuan Yingde Power Supply Bureau, Yingde 513099, ChinaGuangdong Electric Power Co., Ltd., Qingyuan Yingde Power Supply Bureau, Yingde 513099, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaTo address the issue of economic dispatch imbalance in virtual power plant (VPP) systems caused by the influence of operators and distribution networks, this study introduces an optimized economic dispatch method based on bi-level game theory. Firstly, a bi-level game model is formulated, which integrates the operational and environmental expenses of VPPs with the revenues of system operators. To avoid local optima during the search process, an enhanced reinforcement learning algorithm is developed to achieve rapid convergence and obtain the optimal solution. Finally, case analyses illustrate that the proposed method effectively accomplishes multi-objective optimization for various decision-making stakeholders, including VPP and system operators, while significantly reducing curtailment costs associated with the extensive integration of distributed renewable energy. Furthermore, the proposed algorithm achieves fast iteration and yields superior dispatch outcomes under the same modeling conditions.https://www.mdpi.com/1996-1073/18/2/374virtual power plantbi-level gamereinforcement learningpower trading |
| spellingShingle | Zhu Liu Guowei Guo Dehuang Gong Lingfeng Xuan Feiwu He Xinglin Wan Dongguo Zhou Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning Algorithm Energies virtual power plant bi-level game reinforcement learning power trading |
| title | Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning Algorithm |
| title_full | Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning Algorithm |
| title_fullStr | Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning Algorithm |
| title_full_unstemmed | Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning Algorithm |
| title_short | Bi-Level Game Strategy for Virtual Power Plants Based on an Improved Reinforcement Learning Algorithm |
| title_sort | bi level game strategy for virtual power plants based on an improved reinforcement learning algorithm |
| topic | virtual power plant bi-level game reinforcement learning power trading |
| url | https://www.mdpi.com/1996-1073/18/2/374 |
| work_keys_str_mv | AT zhuliu bilevelgamestrategyforvirtualpowerplantsbasedonanimprovedreinforcementlearningalgorithm AT guoweiguo bilevelgamestrategyforvirtualpowerplantsbasedonanimprovedreinforcementlearningalgorithm AT dehuanggong bilevelgamestrategyforvirtualpowerplantsbasedonanimprovedreinforcementlearningalgorithm AT lingfengxuan bilevelgamestrategyforvirtualpowerplantsbasedonanimprovedreinforcementlearningalgorithm AT feiwuhe bilevelgamestrategyforvirtualpowerplantsbasedonanimprovedreinforcementlearningalgorithm AT xinglinwan bilevelgamestrategyforvirtualpowerplantsbasedonanimprovedreinforcementlearningalgorithm AT dongguozhou bilevelgamestrategyforvirtualpowerplantsbasedonanimprovedreinforcementlearningalgorithm |