AI-Enabled Energy Management for Solar Electric Vehicles with Conventional Grid–Integrated DC Microgrid Architecture

This paper presents the design, modeling, and optimization of an Artificial Intelligence (AI)-based solar-powered electric vehicle (SPEV). While solar-electric propulsion promises clean and sustainable mobility, practical range and reliability are constrained by intermittent irradiance, battery degradation, and dynamic driving patterns. We integrate machine learning and control intelligence across three pillars: (1) energy harvesting and power conversion, (2) battery health-aware energy management, and (3) driver/route assistance. A block-level architecture is proposed along with an AI control flow for multi-objective optimization—maximizing range, preserving State of Health (SOH), and minimizing lifecycle cost. We develop a simulation framework and demonstrate improvements in energy efficiency, range, and charge/discharge smoothness compared with a rule-based baseline. Results indicate up to 12–22% efficiency gains across typical urban duty cycles. We conclude with deployment considerations, limitations, and future research directions.