Design of Metaheuristic Optimization with Deep-Learning-Assisted Solar-Operated On-Board Smart Charging Station for Mass Transport Passenger Vehicle

Electric vehicles (EVs) have become popular in reducing the negative impact of ICE automobiles on environment. EVs been predicted to be an important mode mass transit around globe recent years. Several charging stations island and remote areas are dependent off-grid power sources renewable energy. Solar energy is used daytime as it based several environmental components. The creation efficient trackers necessary for solar arrays produce at their peak efficiency. To deliver during emergencies store case there excess, storage systems required. It has long known that reliable battery management technology essential maintaining precise charge levels avoiding overcharging. This study suggests ideal deep-learning-assisted solar-operated off-board smart station (ODL-SOOSCS) design method a result. development on-board main goal ODL-SOOSCS technique being described. In approach described here, perovskite film serves generating module, generates stored module with hybrid ultracapacitor lithium-ion battery. Broad bridge converters panels incorporated into deep belief network (DBN) controller, which doubles EV station. An oppositional bird swarm optimization (OBSO) algorithm hyperparameter optimizer improve performance DBN model. Moreover, MPPT device exploited monitoring providing maximal output panel if PV arrays. proposed system combines metaheuristic algorithms learning techniques create transport passenger vehicles. integration two powerful technologies novel toward solving complex problem electric transportation systems. experimental validation tested distinct converter topologies. A widespread analysis assures promising over other current methodologies.