Electric vehicles (EVs) represent an effective solution for reducing carbon dioxide emissions

provided their lithium-ion batteries (LIBs) are charged by using clean energy and a reliance on traditional fossil-fuel-based electricity generation is avoided. However

given the widespread adoption of EVs

complete reliance on clean energy faces numerous challenges

including the scarcity of available clean energy compared with the enormous demand for charging the batteries of these vehicles. This directly impacts grid performance and overall sustainability. Considering this reality

this study proposes an efficient solution for intelligent maximum power point tracking (MPPT) based on an artificial neural network (ANN) algorithm and the charging of EV batteries using solar photovoltaic (PV) energy through distributed PV systems covering both nearby and remote areas. A clean PV unit of 50 kW is proposed to reduce CO2 emissions by ∼3.7 tons annually compared with conventional fossil-fuel-based power stations by shifting to a clean solution that significantly reduces the negative impact of carbon dioxide emissions. The proposed system focuses on controlling the charging of EV batteries through continuous monitoring of the state of charge and terminal voltage of the LIB to protect the EV battery against overcharging or fully discharging. This design ensures fast and accurate MPPT performance while significantly reducing CO2 emissions. MATLAB®/Simulink® simulation results show promising indicators for an efficient battery charger for EV LIB applications. The simulation results show an efficient ANN algorithm with a low mean squared error of 0.00045023 at epoch 12

a suitable charging current ranging from 20 and 29 A

and a daily charging energy range of 40–60 kWh.