EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Two-Stage PPO–RLMPA Framework for Dynamic Economic Dispatch with Renewable Energy and Storage Integration

Kemal Keskin iD

Biomimetics · 06.06.2026 · 11 (6) · 400

DOI: 10.3390/biomimetics11060400 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 06.06.2026. Verfasst von Kemal Keskin. Beteiligte Einrichtung: Department of Transport and Planning, Delft University of Technology, 2628 CN Delft, The Netherlands. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Dynamic Economic Dispatch (DED) problem underpins the cost-efficient and reliable operation of modern power systems, yet valve-point loading, ramp-rate coupling, and the growing share of intermittent wind, photovoltaic, and pumped-storage hydro (PSH) resources render it highly non-convex. Metaheuristic methods typically require large computational budgets and hand-crafted constraint-handling rules, whereas deep reinforcement learning agents rarely guarantee the feasibility of the schedules they produce. To address both limitations, this paper proposes a Two-Stage PPO–RLMPA framework that couples data-driven policy learning with a biomimetic metaheuristic search inspired by marine predator–prey dynamics. In the first stage, a Proximal Policy Optimization (PPO) agent is trained on a Markov Decision Process reformulation of DED in which a deterministic Safety Layer projects every raw action onto the feasible set defined by capacity, ramp-rate, and power-balance constraints, so the policy only observes physically viable transitions. In the second stage, the PPO dispatch is refined by the RLMPA module, a Marine Predators Algorithm (MPA) whose exploration–exploitation balance, Lévy-flight foraging, and Fish Aggregating Devices (FADs) attraction mechanisms emulate strategies documented in marine ecosystems; its step-size factor and FADs probability are further adapted online by a Deep Q-Network. This biomimetics-informed refinement translates predator–prey foraging intelligence into economically efficient thermal dispatch under valve-point non-convexity. Across 30 independent runs on ten- and twenty-unit benchmark systems with wind, PV, and PSH integration, the framework attains best costs of USD 368,763 and USD 737,348 on Test Systems 1 and 2, corresponding to reductions of approximately 1.1% and 4.4% over the CFCEP baseline, with zero post-repair constraint violations in every run.

Schlagwörter

Stichwörter der Autor:innen

Deep Q-NetworkHybrid OptimizationMarine Predators AlgorithmProximal Policy OptimizationRLMPARenewable Energy Integrationdeep reinforcement learningdynamic economic dispatchpumped-storage hydro

Autor:innen und Institutionen

  • Department of Transport and Planning, Delft University of Technology, 2628 CN Delft, The Netherlands.
  • Department of Electrical and Electronics Engineering, Eskisehir Osmangazi University, Eskisehir 26040, Turkey.

ORCID-Profile: Kemal Keskin

Zitieren

APA

Keskin, K. (2026). A Two-Stage PPO–RLMPA Framework for Dynamic Economic Dispatch with Renewable Energy and Storage Integration. Biomimetics, 11(6), 400. https://doi.org/10.3390/biomimetics11060400

Vancouver

Keskin K. A Two-Stage PPO–RLMPA Framework for Dynamic Economic Dispatch with Renewable Energy and Storage Integration. Biomimetics. 2026;11(6):400. doi:10.3390/biomimetics11060400

BibTeX
@article{Keskin2026,
  author = {Keskin, Kemal},
  title = {A Two-Stage PPO–RLMPA Framework for Dynamic Economic Dispatch with Renewable Energy and Storage Integration},
  journal = {Biomimetics},
  year = {2026},
  volume = {11},
  number = {6},
  pages = {400},
  doi = {10.3390/biomimetics11060400}
}
Kostenlos starten →