Optimal Charge Scheduling and Navigation for Multiple EV Using Deep Reinforcement Learning and Whale Optimization

The demand for Electric Vehicles (EVs) is increasing exponentially in recent times because of its ability to minimize energy savings and carbon emission. However, the charging process and charging option increases the challenges for EV adoption. With the growing adaptability to EVs, the need for addressing the challenges related to limited range and the availability of charging infrastructure becomes crucial. This paper presents an optimized deep learning-based charge scheduling approach in EVs for intelligent transport systems. The study leverages the Deep Reinforcement Learning (DRL) for making real-time decisions. The DRL model is trained using various features such as Battery critical percentage (SOC), time slots, nearest charge station, and availability of charging station. The features are optimized using a nature inspired Whale Optimization Algorithm (WOA), which helps in obtaining optimal charge scheduling. The proposed approach is experimentally evaluated in terms of reducing the tow counts in the selected region. Results from the experimental analysis validate the efficacy of the proposed approach in achieving optimal charge scheduling and navigation for EVs.