EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Data-Driven Multi-Agent Reinforcement Learning Approach for Voltage Control Under Weak Grid Support

Jiaxin Wu, Ziqi Wang, Ji Han iD, Qionglin Li, Ran Sun, Chenhao Li, Yuehan Cheng, Bokai Zhou, Jiaming Guo, Bocheng Long

Sensors · 04.12.2025 · 25 (23) · 7399

DOI: 10.3390/s25237399 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.12.2025. Verfasst von Jiaxin Wu und 9 weiteren Autor:innen. Beteiligte Einrichtung: State Grid Henan Electric Power Company, Zhengzhou 450052, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address active voltage control in photovoltaic (PV)-integrated distribution networks characterized by weak voltage support conditions, this paper proposes a multi-agent deep reinforcement learning (MADRL)-based coordinated control method for PV clusters. First, the voltage control problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP), and a centralized training with decentralized execution (CTDE) framework is adopted, enabling each inverter to make independent decisions based solely on local measurements during the execution phase. To balance voltage compliance with energy efficiency, two barrier functions are designed to reshape the reward function, introducing an adaptive penalization mechanism: a steeper gradient in violation region to accelerate voltage recovery to the nominal range, and a gentler gradient in the safe region to minimize excessive reactive regulation and power losses. Furthermore, six representative MADRL algorithms—COMA, IDDPG, MADDPG, MAPPO, SQDDPG, and MATD3—are employed to solve the active voltage control problem of the distribution network. Case studies based on a modified IEEE 33-bus system demonstrate that the proposed framework ensures voltage compliance while effectively reducing network losses. The MADDPG algorithm achieves a Controllability Ratio (CR) of 91.9% while maintaining power loss at approximately 0.0695 p.u., demonstrating superior convergence and robustness. Comparisons with optimal power flow (OPF) and droop control methods confirm that the proposed approach significantly improves voltage stability and energy efficiency under model-free and communication-constrained weak grid conditions.

Schlagwörter

Stichwörter der Autor:innen

barrier functiondistributed controldistributed photovoltaicsdistribution networkmulti-agent deep reinforcement learning

Autor:innen und Institutionen

  • State Grid Henan Electric Power Company, Zhengzhou 450052, China.
  • College of New Energy, Harbin Institute of Technology at Weihai, Weihai 264200, China.
  • Electric Power Research Institute of State Grid Henan Electric Power Company, Zhengzhou 450052, China.

ORCID-Profile: Ji Han

Zitieren

APA

Wu, J., Wang, Z., Han, J., Li, Q., Sun, R., Li, C., Cheng, Y., Zhou, B., Guo, J., & Long, B. (2025). A Novel Data-Driven Multi-Agent Reinforcement Learning Approach for Voltage Control Under Weak Grid Support. Sensors, 25(23), 7399. https://doi.org/10.3390/s25237399

Vancouver

Wu J, Wang Z, Han J, Li Q, Sun R, Li C, et al. A Novel Data-Driven Multi-Agent Reinforcement Learning Approach for Voltage Control Under Weak Grid Support. Sensors. 2025;25(23):7399. doi:10.3390/s25237399

BibTeX
@article{Wu2025,
  author = {Wu, Jiaxin and Wang, Ziqi and Han, Ji and Li, Qionglin and Sun, Ran and Li, Chenhao and Cheng, Yuehan and Zhou, Bokai and Guo, Jiaming and Long, Bocheng},
  title = {A Novel Data-Driven Multi-Agent Reinforcement Learning Approach for Voltage Control Under Weak Grid Support},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {23},
  pages = {7399},
  doi = {10.3390/s25237399}
}
Kostenlos starten →