A Hybrid Model Combining Improved Weighted Wolf Optimization and Reinforcement Learning for Estimating Electric Vehicle Travel Time

With the rapid increase in Electric Vehicles (EVs), the issue of charging them has received a lot of attention. Since one EV’s charging time cannot be cut quickly and the number of charging stations will not expand quickly, scheduling EV charging operations in metropolitan areas becomes vital as it can boost charging efficiency and minimize EV users’ concern over charging. There isn’t currently a useful scheduling software product available in this industry. Effective trip time prediction is essential for charging stop scheduling and route optimization, especially for EVs attempting to maneuver through intricate metropolitan areas.In order to precisely predict trip durations for EVs, this research presents a unique hybrid model that combines the Reinforcement Learning (RL) and Improved Weighted Wolf Optimization (IWWO) algorithms. The model's capacity to identify complex patterns in traffic data is improved by optimizing the selection of pertinent features and parameters via the use of the IWWO algorithm. The model's performance is then adjusted using RL approaches, which use iterative learning and adaptability to changing traffic circumstances. The suggested hybrid approach provides reliable and flexible EV travel time estimate by using the advantages of both optimization and machine learning paradigms. The outcomes of the experiments show how well the suggested method works in estimating trip times, especially in situations with erratic traffic patterns and variable ambient factors. With the use of this hybrid model, EV travel time prediction has advanced significantly, enabling more effective route planning and charge management to promote sustainable urban transportation.