B. Younes - Laboratory of The Applied and Automation and Industial Diagnostic (LAADI), University of Djelfa, Djelfa, Algeria
H. Ait Abbas - Laboratory of Electrical and Automatic Systems Engineering (LGSEA), University of Bouira, Bouira, Algeria
K. Laroussi - Laboratory of The Applied and Automation and Industial Diagnostic (LAADI), University of Djelfa, Djelfa, Algeria
A. Bousbaine - College of Science and Engineering, University of Derby, Derby, United Kingdom
O. Fergani - Laboratory of Identification, Commande, Control and Communication (LI۳CUB), University of Biskra, Algeria
A. Mazari - Laboratory of The Applied and Automation and Industial Diagnostic (LAADI), University of Djelfa, Djelfa, Algeria

In addressing the critical challenge of developing sustainable energy solutions for electric vehicle (EV) battery charging, this study introduces an innovative direct current (DC) microgrid system optimized for areas with high solar irradiance, such as Ain El Ibel, Djelfa. The research confronts two primary difficulties: maximizing solar energy utilization in the microgrid system and ensuring system stability and response accuracy for reliable EV charging. To tackle these challenges, the study presents two original achievements. Firstly, it develops a neural network-enhanced Maximum Power Point Tracking (MPPT) controller, which is further optimized with Particle Swarm Optimization (PSO) to increase the efficiency of solar energy capture. Secondly, it refines the system's reliability through the advanced calibration of a Fractional Order Proportional-Integral (FOPI) controller using the Grey Wolf Optimization (GWO) technique, marking a notable improvement in microgrid system stability and response accuracy. The integration of a solar panel array, battery storage, and a supercapacitor, coupled with these advanced optimization techniques, exemplifies a significant leap forward in enhancing efficiency and reliability of EV battery charging through renewable energy sources. Comprehensive simulation and evaluation of the system underscore its superiority over conventional methods, demonstrating the effectiveness of combining neural network-based optimization with PSO and GWO. This breakthrough not only advances the field of renewable energy, particularly for solar-powered EV charging stations, but also aligns with global efforts towards sustainable transportation solutions.

DC microgrid system, Maximum power point tracking, Grey Wolf Optimization, Particle Swarm Optimization, Fractional Order Proportional-Integral Controller, Neuronal Network