Loading...
Dr. H. Joseph Prabhakar Williams is an Associate Professor in the Department of Electronics and Communication Engineering at Sri Krishna College of Engineering and Technology, Coimbatore, Tamil Nadu, India. His research interests include Artificial Intelligence, embedded systems, Internet of Things, intelligent communication systems, and machine learning applications. He is actively engaged in teaching, research, and innovation in emerging engineering technologies.
The growing prevalence of Electric Vehicles (EVs) has intensified the demand for smart charging infrastructure that can reduce charging duration, optimise battery efficiency, and augment user convenience. Precise forecasting of electric vehicle charging duration is crucial for enhancing charging station efficiency, minimising wait times, advancing energy management, and facilitating smart grid functionality. Traditional charge estimating techniques frequently overlook dynamic elements such battery State of Charge (SOC), battery condition, charging power, environmental temperature, charging station accessibility, driving patterns, and traffic circumstances. Machine Learning (ML), Artificial Intelligence (AI), Internet of Things (IoT), Cloud Computing, Edge Computing, and Explainable Artificial Intelligence (XAI) offer sophisticated methods for accurately forecasting charging times. Through the ongoing examination of both historical and real-time charging information, machine learning models provide astute charging scheduling, route optimisation, battery enhancement, and energy-efficient transit. This chapter elucidates the principles, framework, machine learning methodologies, applications, obstacles, and prospective research avenues related to the prediction of electric car charging durations using machine learning.