Artificial Intelligence-Based MPPT and Energy Management for Solar-Battery EV Charging Stations: Literature Review and Research Gaps

The increasing adoption of electric vehicles (EVs) has created a need for efficient, reliable, and renewable-energy-based charging infrastructure. Solar photovoltaic (PV) generation can reduce the dependence of EV charging stations on utility-grid power; but, variations in solar irradiation and temperature continuously affect PV operating conditions. For that reason, efficient maximum power point tracking (MPPT) is essential for extracting available solar power. Conventional methods such as Perturb and Observe (P&O) and Incremental Conductance (INC) may experience oscillations, slower response, and reduced performance under rapidly changing and partially shaded conditions. Intelligent optimization algorithms, including Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), Whale Optimization Algorithm (WOA), and Ant Lion Optimization (ALO), offer potential for improved PV power extraction. Effective EV charging also requires coordination among PV generation, battery state of charge (SOC), EV charging demand, and grid power. This paper formulates an integrated research problem combining intelligent MPPT with energy management for a solar-battery-powered EV charging station. A focused literature review is presented, and key research gaps are identified, particularly the limited integration of intelligent MPPT with EMS and the limited direct comparison of PSO, GWO, WOA, and ALO under identical operating conditions. These gaps establish the basis for developing a unified AI-based MPPT and energy management framework.