Enhancing electric vehicle charging safety and efficiency through hybrid charging systems and intelligent management strategies

The rise of electric vehicles (EVs) is a necessity shortly, given their ability to decrease carbon emissions and environmental impact, thus slowing down the rate of climate change. This manuscript proposes enhancing EV charging safety and efficiency by implementing a hybrid charging system and intelligent management strategies. The proposed scheme integrates an updated wave search graph bidirectional convolutional neural network (UWSGBCNN) and giant trevally tunicate swarm optimizer (GTTSO) called the UWSGBCNN-GTTSO approach. The main aim of the proposed study is to enhance EV charging safety with a hybrid charging system, that integrates various charging modes (e.g., fast charging, wireless charging) to optimize charging times and minimize energy loss. The updated wave search graph bidirectional convolutional neural network enables real-time data analysis and proactive fault detection, while the giant trevally tunicate swarm optimizer optimizes charging schedules and routes. The proposed UWSGBCNN-GTTSO method is executed in the MATLAB tool, and validated their performance is validated with various prevailing methods such as genetic algorithm, artificial neural network, and particle swarm optimization. The efficiency and cost of the developed method are 50.237<euro>, and 97 %, respectively. It shows the high safety of EV charging in the hybrid EV charging station.