Title: Artificial intelligence and machine learning-based decision support system for forecasting electric vehicles' power requirement

Author (s):: Jauhar S.K.; Sethi S.; Kamble S.S.; Mathew S.; Belhadi A.

Journal: Technological Forecasting and Social Change

Month and Year: April 2024

Abstract: Increasing pollution is causing adverse environmental effects, leading to increased interest in combating this issue. There has been a significant interest in minimizing the pollution caused by combustion engine vehicles, with high research and development investments in hybrid and electric vehicle (EV) batteries. The innovations in EVs have a high potential to contribute to an optimized transportation sector while also playing a crucial role in reducing greenhouse gas emissions. This study contributes to the EV industry by precisely predicting the power demand at a particular charging station and identifying the optimal charging station characteristics. We proposed a modified business process based on digital technologies to maximize customer engagement and operational efficiency. Our research has incorporated technologies like artificial intelligence (AI) and machine learning (ML). This study addresses the issues of EV infrastructure facilities, the issues raised by the lack of service features for EVs, and the optimal power requirement for charging stations. The proposed framework has managerial and technological implications, suggesting that the system must promptly receive, store, and analyze substantial volumes of data and demonstrate adaptability in response to environmental factors, such as the availability of EVs and the utilization of renewable energy sources. Despite the challenges, there is potential promise in developing decision assistance systems for electric vehicle power demands based on AI and ML. © 2024 The Authors

Document Type: Article

DOI: https://doi.org/10.1016/j.techfore.2024.123396