EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Shaped MDPs for Safe Reinforcement Learning of Reactive-Current Injection During Voltage Sags in Inverter-Based Distributed Generation

Mohana Fathollahi, Antonio Camacho Santiago, Cecilio Angulo, Josue Duarte

Electronics · 12.11.2026 · 15 (22) · 5247

DOI: 10.3390/electronics15225247 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 12.11.2026. Verfasst von Mohana Fathollahi und 3 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Secretary of State for Digitalization and Artificial Intelligence, Spanish Ministry of Science, Innovation and Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Renewable energy sources (RESs) challenge grid stability due to their intermittency, particularly during transient disturbances. Voltage sags can rapidly degrade system performance, requiring prompt reactive-current injection to support voltage recovery. Fault ride-through strategies are therefore essential to maintain stable operation of inverter-based systems while complying with grid-code requirements. Traditional analytical and optimization-based methods rely on accurate models and adapt poorly to dynamic conditions. This study proposes a data-driven reinforcement learning (RL) controller, specifically Soft Actor–Critic, for voltage sags in three-phase inverter-based systems, without solving optimization problems. To satisfy grid-code requirements, the proposed method incorporates state-dependent constraints directly into the Markov decision process through transition-function shaping. This approach preserves the original RL algorithm and avoids tuning penalty coefficients. The RL controller follows the same trend as the optimization benchmark across different reference-power levels. The results show that under various severe voltage-sag conditions, the mean absolute error of the RL predictions relative to the optimization results remains below 0.5A. The controller also generalizes across a broader range of operating conditions and uses a simpler training structure than previous RL-based studies. In addition, laboratory experiments further demonstrate its effectiveness in supporting the grid during voltage sags.

Förderung

  • Secretary of State for Digitalization and Artificial Intelligence
  • Spanish Ministry of Science, Innovation and Universities

Zitieren

APA

Fathollahi, M., Santiago, A. C., Angulo, C., & Duarte, J. (2026). Shaped MDPs for Safe Reinforcement Learning of Reactive-Current Injection During Voltage Sags in Inverter-Based Distributed Generation. Electronics, 15(22), 5247. https://doi.org/10.3390/electronics15225247

Vancouver

Fathollahi M, Santiago AC, Angulo C, Duarte J. Shaped MDPs for Safe Reinforcement Learning of Reactive-Current Injection During Voltage Sags in Inverter-Based Distributed Generation. Electronics. 2026;15(22):5247. doi:10.3390/electronics15225247

BibTeX
@article{Fathollahi2026,
  author = {Fathollahi, Mohana and Santiago, Antonio Camacho and Angulo, Cecilio and Duarte, Josue},
  title = {Shaped MDPs for Safe Reinforcement Learning of Reactive-Current Injection During Voltage Sags in Inverter-Based Distributed Generation},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5247},
  doi = {10.3390/electronics15225247}
}
Kostenlos starten →