EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Hierarchical EMS for Virtual Power Plants Using Hybrid Machine Learning and Swarm‐Based Optimization

Arooj Fatima, Muhammad Umair Iftikhar, Syed Ali Abbas Kazmi, Muhammad Waseem

Journal of Electrical and Computer Engineering · 2026-01 · 2026 (1)

DOI: 10.1155/jece/5732396 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Electrical and Computer Engineering, online erschienen am 13.11.2026. Verfasst von Arooj Fatima und 3 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a hierarchical energy management system (EMS) for a virtual power plant (VPP) integrating renewable energy resources, solar, wind and battery storage, with residential load dispatch in smart grid distribution systems (SGDSs). The decentralization of the proposed VPP is maintained using intelligent multiagent‐based modelling (M‐ABM) while preserving prosumer preferences through an efficient communication architecture. Two machine learning (ML) algorithms, linear regression (LR) and random forest (RF), are evaluated for power generation forecasting. RF achieves superior accuracy of 92.04% ( R 2 = 0.9203) for solar and 89.10% ( R 2 = 0.8909) for wind forecasting, outperforming LR, which yields 67.06% and 32.80%, respectively, demonstrating RF’s stronger capability in capturing nonlinear atmospheric relationships. Four metaheuristic algorithms, artificial bee colony optimization (ABCO), grey wolf optimization (GWO), squirrel search optimization (SSO) and salp swarm algorithm (SSA), are evaluated for appliance scheduling and power optimization under a cost‐minimization objective. SSO consistently achieves the best results across all technical, economic and environmental metrics, recording the lowest total bill of vicinity (TBV) of $0.944, minimum total electricity consumption of 21.65 kWh, lowest carbon footprint of 7.3 kg per day and maximum reserved power of 28.34 kWh. The optimal VPP configuration combining RF for generation forecasting and SSO for load optimization yields the most efficient, cost‐effective and environmentally responsible EMS operation. The results are validated on a real‐world dataset from Berkeley, CA, covering 2 years of solar and wind generation data across all four seasons.

Zitieren

APA

Fatima, A., Iftikhar, M. U., Kazmi, S. A. A., & Waseem, M. (2026). A Novel Hierarchical EMS for Virtual Power Plants Using Hybrid Machine Learning and Swarm‐Based Optimization. Journal of Electrical and Computer Engineering, 2026(1). https://doi.org/10.1155/jece/5732396

Vancouver

Fatima A, Iftikhar MU, Kazmi SAA, Waseem M. A Novel Hierarchical EMS for Virtual Power Plants Using Hybrid Machine Learning and Swarm‐Based Optimization. Journal of Electrical and Computer Engineering. 2026;2026(1). doi:10.1155/jece/5732396

BibTeX
@article{Fatima2026,
  author = {Fatima, Arooj and Iftikhar, Muhammad Umair and Kazmi, Syed Ali Abbas and Waseem, Muhammad},
  title = {A Novel Hierarchical EMS for Virtual Power Plants Using Hybrid Machine Learning and Swarm‐Based Optimization},
  journal = {Journal of Electrical and Computer Engineering},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/jece/5732396}
}
Kostenlos starten →