EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Topology-Aware Graph Reinforcement Learning for Voltage-Reactive Power Control in Grid-Connected Microgrids

Yunfei Zhang, Kefan Bao, Gaige Liang, Wennan Zhuang, Longlong Qiang, Difei Tang, Xiangyu Lu, Mingxiao Zhang

Electricity · 22.06.2026 · 7 (2) · 60

DOI: 10.3390/electricity7020060 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electricity, online erschienen am 22.06.2026. Verfasst von Yunfei Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of State Grid Jiangsu Electric Power Company.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the global energy transition accelerates, distribution systems are integrating increasing shares of inverter-interfaced renewables, making reliable voltage support a key operational requirement. In grid-connected microgrids, especially weak radial feeders in rural and remote areas, voltage-reactive power (Volt/Var) control must coordinate multiple inverters under uncertainty from photovoltaic (PV) intermittency, load volatility, and point-of-common-coupling (PCC) disturbances. Existing droop, model-based optimization, and non-graph reinforcement learning (RL) approaches often rely on fixed rules or do not explicitly exploit electrical topology, which limits adaptive coordination. To address this gap, we propose a topology-aware graph reinforcement learning framework for voltage-reactive power control in grid-connected microgrids under uncertainty. The method encodes node states with a graph convolutional network (GCN) and learns coordinated PV/storage reactive-power actions via proximal policy optimization (PPO) with a multi-objective reward balancing voltage quality, control effort, and action smoothness. In a controlled comparison against a multilayer perceptron (MLP)-PPO baseline with identical action space, reward, and PPO objective, our method reduces voltage violation rate (VVR) from 0.0316 ± 0.0086 to 0.0048 ± 0.0019. Additional validation on a modified IEEE 33-bus feeder further reduces VVR from 0.00726 for MLP-PPO and 0.02999 for Droop control to 0.00095, supporting the effectiveness of topology-aware state representation on a larger radial benchmark feeder.

Förderung

  • Science and Technology Project of State Grid Jiangsu Electric Power Company

Zitieren

APA

Zhang, Y., Bao, K., Liang, G., Zhuang, W., Qiang, L., Tang, D., Lu, X., & Zhang, M. (2026). Topology-Aware Graph Reinforcement Learning for Voltage-Reactive Power Control in Grid-Connected Microgrids. Electricity, 7(2), 60. https://doi.org/10.3390/electricity7020060

Vancouver

Zhang Y, Bao K, Liang G, Zhuang W, Qiang L, Tang D, et al. Topology-Aware Graph Reinforcement Learning for Voltage-Reactive Power Control in Grid-Connected Microgrids. Electricity. 2026;7(2):60. doi:10.3390/electricity7020060

BibTeX
@article{Zhang2026,
  author = {Zhang, Yunfei and Bao, Kefan and Liang, Gaige and Zhuang, Wennan and Qiang, Longlong and Tang, Difei and Lu, Xiangyu and Zhang, Mingxiao},
  title = {Topology-Aware Graph Reinforcement Learning for Voltage-Reactive Power Control in Grid-Connected Microgrids},
  journal = {Electricity},
  year = {2026},
  volume = {7},
  number = {2},
  pages = {60},
  doi = {10.3390/electricity7020060}
}
Kostenlos starten →