EUVIMEDEUVIMED entdecken
Crossref

MPC-Guided Deep Reinforcement Learning for Real-Time Scheduling of Microgrid with Uncertainty

Yilu Zhang, Xiaobing Kong

Distributed Generation & Alternative Energy Journal · 04.06.2026

DOI: 10.13052/dgaej2156-3306.4136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Distributed Generation & Alternative Energy Journal, online erschienen am 04.06.2026. Verfasst von Yilu Zhang und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Microgrid energy management plays a critical role in ensuring the secure and economical operation of microgrids. To address the uncertainty of renewable energy generation, this paper proposes an MPC-guided deep reinforcement learning (DRL)–based intraday scheduling strategy for microgrids. The proposed approach integrates the advantages of model predictive control (MPC) and DRL, where the optimization results of the MPC module are provided as environmental inputs to the DRL agent, and the DRL module interacts with the real microgrid environment to generate compensation actions. This framework not only mitigates the performance degradation caused by uncertainties in model-based methods, but also reduces the search space of DRL, thereby accelerating training convergence and suppressing policy fluctuations. Comparative simulations are conducted against standalone MPC and standalone DRL controllers. The results demonstrate that the proposed strategy can significantly reduce both operational security cost and economic cost, while effectively improving the utilization of renewable energy. Therefore, it provides an innovative solution for the microgrid scheduling problem.

Zitieren

APA

Zhang, Y., & Kong, X. (2026). MPC-Guided Deep Reinforcement Learning for Real-Time Scheduling of Microgrid with Uncertainty. Distributed Generation & Alternative Energy Journal. https://doi.org/10.13052/dgaej2156-3306.4136

Vancouver

Zhang Y, Kong X. MPC-Guided Deep Reinforcement Learning for Real-Time Scheduling of Microgrid with Uncertainty. Distributed Generation & Alternative Energy Journal. 2026. doi:10.13052/dgaej2156-3306.4136

BibTeX
@article{Zhang2026,
  author = {Zhang, Yilu and Kong, Xiaobing},
  title = {MPC-Guided Deep Reinforcement Learning for Real-Time Scheduling of Microgrid with Uncertainty},
  journal = {Distributed Generation & Alternative Energy Journal},
  year = {2026},
  doi = {10.13052/dgaej2156-3306.4136}
}
Kostenlos starten →