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.

The rise of renewables coincides with the shift towards Electrical Vehicles (EVs) posing technical and operational challenges for the energy balance of the local grid. Nowadays, the energy grid cannot deal with a spike in EVs usage leading to a need for more coordinated and grid aware EVs charging and discharging strategies. However, coordinating power flow from multiple EVs into the grid requires sophisticated algorithms and load-balancing strategies as the complexity increases with more control variables and EVs, necessitating large optimization and decision search spaces. In this paper, we propose an EVs fleet coordination model for the day ahead aiming to ensure a reliable energy supply and maintain a stable local grid, by utilizing EVs to store surplus energy and discharge it during periods of energy deficit. The optimization problem is addressed using Harris Hawks Optimization (HHO) considering criteria related to energy grid balancing, time usage preference, and the location of EV drivers. The EVs schedules, associated with the position of individuals from the population, are adjusted through exploration and exploitation operations, and their technical and operational feasibility is ensured, while the rabbit individual is updated with a non-dominated EV schedule selected per iteration using a roulette wheel algorithm. The solution is evaluated within the framework of an e-mobility service in Terni city. The results indicate that coordinated charging and discharging of EVs not only meet balancing service requirements but also align with user preferences with minimal deviations.