Integration of Renewable Resources in Electric Vehicle Charging Management Systems Using Deep Learning for Monitoring and Optimization

In recent years, the energy sector has been experienced important growth alongside challenges such as load discrimination and economic crises, promoting a shift toward EVs (electric vehicles) as sustainable transportation alternatives. The study emphases on enhancing conventional EV through improved for system for storing energy and their diverse applications. Main objective is to increase the efficiency of energy transfer and storage in EVs by using an SEPIC converter to increase voltage levels while optimizing power extraction via a maximum power point tracking (MPPT) algorithm enhanced by ant colony optimization and particle swarm optimization (PSO). Many existing methods rely on a single resource, leading to higher consumption rates and increased computational time before application. The research investigates these methodologies and implements fault detection within the system via artificial neural networks (ANNs), ensuring reliability and safety in EV operations, which is essential for widespread adoption. The captured energy is stored in high-capacitance lithium-ion batteries, which are known for their efficiency and longevity. This stored direct current energy is converted into AC (alternating current) via an inverter, which powers the BLDC (brushless direct current) motor for EV operations. The performance of the entire system is evaluated through various metrics, including voltage stability, power output total harmonic distortion, and overall power quality. By focusing on these critical components-energy management, fault diagnosis, and performance evaluation-this study aims to contribute valuable insights into optimizing electric vehicle systems and promoting their adaptation as viable solutions for sustainable transportation.