A Modular Digital Twin Platform for Optimization and Control of Electric Vehicles Charging

Electric vehicle (EV) charging requires balancing economic efficiency, environmental sustainability, and user satisfaction under uncertain and time-varying grid conditions. In this work, we present a modular digital twin platform designed to support the analysis, optimization, and real-time management of smart charging systems. The proposed environment allows users to simulate realistic operational scenarios, test different optimization strategies, and assess their impact in terms of cost and CO2 emissions. A key feature of the platform is its interactive and AI-assisted interface, which enables both technical and non-technical users to interpret results and gain insights into system behavior. The framework integrates several advanced optimization models (ranging from cost-minimizing to carbon-aware formulations) within a unified, easily configurable control panel. By combining explainable outputs, flexible model selection, and data-driven scenario generation, the proposed digital twin bridges the gap between theoretical research and practical EV infrastructure management, offering a valuable tool for decision-making and policy evaluation in the transition toward sustainable mobility.