Explainable AI-enabled adaptive fuzzy MPPT and energy management for bifacial PV and battery-powered electric vehicle charging system

Abstract

Abstract The widespread adoption of electric vehicles (EVs) requires efficient, sustainable charging infrastructure. The use of bifacial photovoltaic (PV) panels with battery energy storage systems (BESS) will provide uninterrupted, sustainable power to EV charging stations. This research is a combination of both an Explainable Artificial Intelligence (XAI)-enabled adaptive fuzzy Maximum Power Point Tracking (MPPT) controller and hierarchical rule-based Energy Management System (EMS) of a 10-kW bifacial solar-driven EV charging system in Madan Mohan Malaviya University of Technology (MMMUT), Gorakhpur, India (26.7 N 83.4 E). The suggested design incorporates a 400 V, 50 Ah (20 kWh) Lithium Iron Phosphate (LiFePO4) battery pack and a 10 kVA two-way inverter, which creates a robust hybrid design. RETScreen Expert software was used to retrieve real-time solar irradiance and atmospheric data. XAI-Fuzzy controller achieves a tracking efficiency of 80.9% under partial shading, which is 4.5% points better than the mainstream Perturb and Observe (P&O) algorithm. The EMS will successfully regulate the flow of power among five operational modes, with the grid power quality having a Total Harmonic Distortion (THD) of 2.40%, quite under the IEEE 519 standard limit of 5%. Explainability metrics reported fidelity of 0.96 and consistency of 0.91, with a sparsity index of 0.38, validating correct and interpretable controller behaviour. Simulation results in MATLAB/Simulink show that the proposed model enhances the overall system efficiency and provides reliable grid support for EV charging under different environmental conditions.