EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hierarchical coordinated scheduling algorithm for reactive power and voltage in cross-regional power grids based on multi-agent reinforcement learning

Zhida Lin, Ximing Zhang, Zhengguo Ren iD, Yanning Shao, Yuanfeng Chen

PLOS One · 24.04.2026 · 21 (4) · e0346570

DOI: 10.1371/journal.pone.0346570 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 24.04.2026. Verfasst von Zhida Lin und 4 weiteren Autor:innen. Beteiligte Einrichtung: China Southern Power Grid Company Limited, Guangzhou, Guangdong, China. Hauptthemen laut MEDLINE: Algorithms, Electric Power Supplies. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of strong dynamic coupling, action space dimension explosion, and voltage imbalance in reactive power and voltage scheduling of cross-regional power grids, this paper proposes a hierarchical coordinated scheduling method based on multi-agent reinforcement learning. The method first constructs a multi-agent reinforcement learning framework driven by probabilistic neural networks to perform distributed representation learning on the joint state vectors, achieving high-precision prediction of reactive power and voltage operating states for each node (prediction error MAE < 0.01 p.u.). Building upon the prediction results, a three-layer “prediction-decision-regulation” coordination mechanism is designed, integrating environmental state perception, action space optimization, and dynamic sensitivity analysis. This effectively addresses real-time decision-making challenges in high-dimensional action spaces, reducing average scheduling decision time by approximately 34.2%. Finally, sensitivity-driven feedback regulation achieves real-time balancing of reactive power and voltage at each node, guiding the power grid to converge stably to an optimal power flow state. Experimental results on the IEEE 33-node system demonstrate that the proposed method increases the voltage qualification rate to 98.7%, reduces system power loss by 30.5%, and decreases the maximum voltage magnitude deviation from 1.679 p.u. to 1.589 p.u., significantly outperforming traditional methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsElectric Power SuppliesReinforcement Machine LearningNeural Networks, Computer

Autor:innen und Institutionen

  • China Southern Power Grid Company Limited, Guangzhou, Guangdong, China.

ORCID-Profile: Zhengguo Ren

Zitieren

APA

Lin, Z., Zhang, X., Ren, Z., Shao, Y., & Chen, Y. (2026). Hierarchical coordinated scheduling algorithm for reactive power and voltage in cross-regional power grids based on multi-agent reinforcement learning. PLOS One, 21(4), e0346570. https://doi.org/10.1371/journal.pone.0346570

Vancouver

Lin Z, Zhang X, Ren Z, Shao Y, Chen Y. Hierarchical coordinated scheduling algorithm for reactive power and voltage in cross-regional power grids based on multi-agent reinforcement learning. PLOS One. 2026;21(4):e0346570. doi:10.1371/journal.pone.0346570

BibTeX
@article{Lin2026,
  author = {Lin, Zhida and Zhang, Ximing and Ren, Zhengguo and Shao, Yanning and Chen, Yuanfeng},
  title = {Hierarchical coordinated scheduling algorithm for reactive power and voltage in cross-regional power grids based on multi-agent reinforcement learning},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0346570},
  doi = {10.1371/journal.pone.0346570}
}
Kostenlos starten →