EUVIMEDEUVIMED entdecken
Crossref

Reinforcement Learning-Based Distributed Secondary Frequency Control and Active Power Sharing in Islanded Microgrids With Bandwidth-Conscious Memory-Event-Triggered Mechanism

Shen Yan, Zehao Dou, Zhou Gu

IEEE Transactions on Automation Science and Engineering · 2026 · 23 · 5450-5459

DOI: 10.1109/tase.2026.3668833 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Automation Science and Engineering, 2026. Verfasst von Shen Yan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Jiangsu Province Youth Science and Technology Talent Support Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper studies the reinforcement learning-based distributed secondary frequency control and active power allocation of islanded microgrids under event-triggered mechanism. First, a novel bandwidth-conscious memory-event-triggered mechanism is proposed to reduce communication and computation burdens, which introduces the mean of memory signals to smooth the measured outputs perturbed by disturbances and noises. Meanwhile, a dynamic triggering threshold depending on real-time bandwidth status is constructed to adaptively adjust the data transmission rate according to the changes in bandwidth status and system responses. Second, a new reinforcement learning-based distributed secondary controller using Q-learning algorithm is presented to dynamically regulate the frequency controller gains in response to complex system environments, which helps in achieving better frequency restoration performance. Third, the system stability is analyzed by some linear matrix inequality conditions. Then, simulation outcomes based on load variation and plug-and-play test illustrate that our strategy achieves satisfactory performance in frequency restoration and active power sharing. In addition, some comparison results show the merits of the constructed event-triggered scheme and Q-learning-based distributed secondary frequency controller. Note to Practitioners—This article is concerned with the reinforcement learning-based distributed secondary frequency control and active power allocation of islanded microgrids, addressing challenges induced by limited communication resources, dynamic bandwidth status and complex operation environment. The innovative bandwidth-conscious memory-event-triggered scheme increases the usage efficiency of communication network, and the reinforcement learning-based distributed secondary frequency controller optimizes the frequency restoration performance for islanded microgrids under load changes and random plug and unplug behaviors. The developed strategy is able to handle these realistic problems in practical systems. This strategy can provide technical support for electrical engineers to enhance the stability performance of islanded microgrids.

Förderung

  • National Natural Science Foundation of China
  • Jiangsu Province Youth Science and Technology Talent Support Project

Zitieren

APA

Yan, S., Dou, Z., & Gu, Z. (2026). Reinforcement Learning-Based Distributed Secondary Frequency Control and Active Power Sharing in Islanded Microgrids With Bandwidth-Conscious Memory-Event-Triggered Mechanism. IEEE Transactions on Automation Science and Engineering, 23, 5450-5459. https://doi.org/10.1109/tase.2026.3668833

Vancouver

Yan S, Dou Z, Gu Z. Reinforcement Learning-Based Distributed Secondary Frequency Control and Active Power Sharing in Islanded Microgrids With Bandwidth-Conscious Memory-Event-Triggered Mechanism. IEEE Transactions on Automation Science and Engineering. 2026;23:5450-5459. doi:10.1109/tase.2026.3668833

BibTeX
@article{Yan2026,
  author = {Yan, Shen and Dou, Zehao and Gu, Zhou},
  title = {Reinforcement Learning-Based Distributed Secondary Frequency Control and Active Power Sharing in Islanded Microgrids With Bandwidth-Conscious Memory-Event-Triggered Mechanism},
  journal = {IEEE Transactions on Automation Science and Engineering},
  year = {2026},
  volume = {23},
  pages = {5450--5459},
  doi = {10.1109/tase.2026.3668833}
}
Kostenlos starten →