EUVIMEDEUVIMED entdecken
Crossref

Hierarchical Reinforcement Learning for Degradation-Aware and Coordinated Control of Virtual Power Plants

Arjun M., Siyuan Wang, Manojkumar Ramteke, Hariprasad Kodamana, Fengqi You

Industrial & Engineering Chemistry Research · 06.11.2026

DOI: 10.1021/acs.iecr.6c03278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Industrial & Engineering Chemistry Research, online erschienen am 06.11.2026. Verfasst von Arjun M. und 4 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: Anusandhan National Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Virtual Power Plants (VPPs) coordinate distributed energy resources (DERs) under forecast uncertainty and multi-time-scale constraints, while battery and generator wear can erase short-term trading gains. This paper proposes a hierarchical reinforcement learning (HRL) controller that matches aggregator practice: a slow-time-scale manager issues location-level power subgoals together with a continuous autonomy signal, and fast-time-scale workers dispatch devices under local physics. Battery and generator degradation enter the training reward through a three-phase curriculum that activates a throughput-budget penalty and a cycle-depth surcharge, so the policy optimizes profit net of wear rather than arbitrage alone. On a 100-day shared-seed benchmark against two decentralized RL controllers, an open-loop stochastic mixed-integer programming (MIP) day-ahead optimizer, and a closed-loop model predictive control (MPC) baseline that reoptimizes hourly over an 8-h horizon, HRL attains an average daily profit of \$50,264─3.1× MPC and 4.0× MIP─at 50–170 ms per simulated day. HRL is the only method whose throughput-to-cycle-depth ratio exceeds unity (1.18), and it incurs only \$24.6 of cycle-depth-aware wear per \$1,000 of profit (2.5× better than MPC). These results indicate that degradation-aware hierarchical control can outperform both open-loop stochastic optimization and receding-horizon MPC for real-time VPP dispatch.

Förderung

  • Anusandhan National Research Foundation

Zitieren

APA

M., A., Wang, S., Ramteke, M., Kodamana, H., & You, F. (2026). Hierarchical Reinforcement Learning for Degradation-Aware and Coordinated Control of Virtual Power Plants. Industrial & Engineering Chemistry Research. https://doi.org/10.1021/acs.iecr.6c03278

Vancouver

M. A, Wang S, Ramteke M, Kodamana H, You F. Hierarchical Reinforcement Learning for Degradation-Aware and Coordinated Control of Virtual Power Plants. Industrial & Engineering Chemistry Research. 2026. doi:10.1021/acs.iecr.6c03278

BibTeX
@article{M2026,
  author = {M., Arjun and Wang, Siyuan and Ramteke, Manojkumar and Kodamana, Hariprasad and You, Fengqi},
  title = {Hierarchical Reinforcement Learning for Degradation-Aware and Coordinated Control of Virtual Power Plants},
  journal = {Industrial & Engineering Chemistry Research},
  year = {2026},
  doi = {10.1021/acs.iecr.6c03278}
}
Kostenlos starten →