A Digital Twin for Real-Time and Predictive Optimization of Electric Vehicle Charging in Microgrids Integrating Renewable Energy Sources
Energies · 24.10.2025 · 18 (21) · 5605
DOI: 10.3390/en18215605 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energies, online erschienen am 24.10.2025. Verfasst von Tancredi Testasecca und 3 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.
Abstract (Originalsprache)
Global electric vehicle sales are growing exponentially, with the European Union actively promoting the adoption of electric vehicles to significantly reduce mobility-related emissions. Concurrently, research efforts are increasingly directed toward optimizing vehicle charging strategies for the effective integration of renewable energy sources. Nevertheless, despite extensive theoretical studies, few practical implementations have been carried out. In response, this paper presents a digital twin of a microgrid designed specifically for optimizing the charging schedules of an electric vehicle fleet, with the goal of maximizing photovoltaic self-consumption. Machine learning algorithms are utilized to forecast vehicle energy consumption, and various heuristic optimization methods are applied to determine optimal charging schedules. The system incorporates an interactive dashboard, enabling users to input specific preferences or delegate charging decisions to a real-time optimizer. Additionally, a user-centric decision support system was developed to provide recommendations on optimal vehicle connection timings and heat pump setpoints. Certain algorithms failed to converge on a feasible optimal solution, even after 340 s and over 500 generations, particularly within high-production scenarios. Conversely, using the GWO-WOA algorithm, optimal charging schedules are computed in less than 25 s, balancing photovoltaic power exports under varying weather conditions. Furthermore, K-Means was identified as the most effective clustering technique, achieving a Silhouette Score of up to 0.57 with four clusters. This configuration resulted in four distinct velocity ranges, within which energy consumption varied by up to 5.8 kWh/100 km, depending on the vehicle’s velocity. Finally, the facility managers positively assessed the usability of the DT dashboard and the effectiveness of the decision support system.
Förderung
- European Union
Zitieren
APA
Testasecca, T., Bellesini, F., Arnone, D., & Beccali, M. (2025). A Digital Twin for Real-Time and Predictive Optimization of Electric Vehicle Charging in Microgrids Integrating Renewable Energy Sources. Energies, 18(21), 5605. https://doi.org/10.3390/en18215605
Vancouver
Testasecca T, Bellesini F, Arnone D, Beccali M. A Digital Twin for Real-Time and Predictive Optimization of Electric Vehicle Charging in Microgrids Integrating Renewable Energy Sources. Energies. 2025;18(21):5605. doi:10.3390/en18215605
BibTeX
@article{Testasecca2025,
author = {Testasecca, Tancredi and Bellesini, Francesco and Arnone, Diego and Beccali, Marco},
title = {A Digital Twin for Real-Time and Predictive Optimization of Electric Vehicle Charging in Microgrids Integrating Renewable Energy Sources},
journal = {Energies},
year = {2025},
volume = {18},
number = {21},
pages = {5605},
doi = {10.3390/en18215605}
}
EUVIMED