Market-Aware and Topology-Embedded Safe Reinforcement Learning for Virtual Power Plant Dispatch
World Electric Vehicle Journal · 21.04.2026 · 17 (4) · 222
DOI: 10.3390/wevj17040222 ↗Kurz gefasst
Fachartikel in der Zeitschrift World Electric Vehicle Journal, online erschienen am 21.04.2026. Verfasst von Yueping Xiang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the State Grid Sichuan Electric Power Company.
Abstract (Originalsprache)
To address the challenges faced by virtual power plants (VPPs) in uncertain market environments and complex distribution networks, including strong market coupling, difficulty in multi-resource coordination, and strict safety constraints, this paper proposes a Hierarchical Hybrid Intelligent Framework (H2IF). The proposed framework integrates a market-aware meta-game mechanism, a topology-embedded graph attention coordination method, and a risk-aware soft/hard constraint safety mechanism to achieve economically optimal dispatch of VPPs in complex dynamic scenarios. By explicitly modeling competitive market interactions, the proposed method enhances strategy robustness; by exploiting grid topology priors, it improves multi-agent coordination capability; and by combining differentiable projection with risk-constrained optimization, it jointly ensures operational safety and revenue stability. Simulation results on a modified IEEE 33-bus system demonstrate that H2IF outperforms mainstream deep reinforcement learning methods and rule-based dispatch strategies in overall performance. In the 24 × 300-step testing scenario, H2IF achieves an average single-episode operating cost of 38.23 k$, which is 28.9%, 40.4%, and 26.5% lower than those of MADDPG, SAC, and the rule-based method, respectively, while also yielding the lowest constraint violation level. Ablation studies further verify the effectiveness of each key module in improving profit, reducing operating costs, enhancing tracking performance, and strengthening safety. The results indicate that the proposed method enables coordinated optimization of economy, safety, and robustness for VPP dispatch under uncertain market and operating conditions.
Förderung
- the State Grid Sichuan Electric Power Company
Zitieren
APA
Xiang, Y., Li, L., Hou, Y., Dai, X., Peng, W., Liu, Z., Liu, Z., Chen, Z., Hu, X., & He, L. (2026). Market-Aware and Topology-Embedded Safe Reinforcement Learning for Virtual Power Plant Dispatch. World Electric Vehicle Journal, 17(4), 222. https://doi.org/10.3390/wevj17040222
Vancouver
Xiang Y, Li L, Hou Y, Dai X, Peng W, Liu Z, et al. Market-Aware and Topology-Embedded Safe Reinforcement Learning for Virtual Power Plant Dispatch. World Electric Vehicle Journal. 2026;17(4):222. doi:10.3390/wevj17040222
BibTeX
@article{Xiang2026,
author = {Xiang, Yueping and Li, Luoyi and Hou, Yanqiu and Dai, Xiaoyu and Peng, Wenfeng and Liu, Zhuoyang and Liu, Ziming and Chen, Zicong and Hu, Xingyu and He, Lv},
title = {Market-Aware and Topology-Embedded Safe Reinforcement Learning for Virtual Power Plant Dispatch},
journal = {World Electric Vehicle Journal},
year = {2026},
volume = {17},
number = {4},
pages = {222},
doi = {10.3390/wevj17040222}
}
EUVIMED