Key points are not available for this paper at this time.
The transition towards electric vehicles (EVs) necessitates the development of efficient and reliable charging infrastructure. This paper presents an AI-driven approach to optimize EV infrastructure, focusing on five key aspects: profiling, augmentation, forecasting, explainability, and charging efficiency. Profiling involves understanding EV drivers' behaviors and preferences, facilitating targeted infrastructure development. Augmentation utilizes AI algorithms to identify optimal locations for new charging stations or upgrades based on usage patterns and demand forecasts. Forecasting models leverage machine learning techniques to predict future EV adoption rates and charging demands, aiding in infrastructure planning. These datasets can be used to generate insights and decisions through the use of artificial intelligence (AI) algorithms. A thorough analysis of the usefulness of AI in charge-demand profiling, data augmentation, demand forecasting, demand explainability, and charge optimization of the EVI has not yet been conducted, despite a number of recent studies in this area. This study's goal was to create, develop, and assess a thorough AI framework that fills in this EVI gap. The findings of an empirical assessment of this AI framework on an actual EVI case study validate its usefulness in tackling the new issues surrounding dispersed energy resources in the deployment of EVs.
Gopinath Singaram (2024) studied this question.