Sustainable e-mobility with controlled charging scheme based on grid energy using machine learning

Abstract

The electric vehicle (EV) popularity has taken off among consumers, which has in turn led to efforts to create an efficient EV charging infrastructure. This paper addresses this challenge by proposing a scheduled charging scheme that uses real-time data from a grid-connected charging station at Baner, Pune, operated by Pune Mahanagar Parivahan Mahamandal Ltd (PMPML). The proposed system makes use of advanced machine learning techniques such as the Stochastic dual coordinate ascent (SDCA) and Fast Forest (FF) algorithm, both of which allow for precise and efficient computations to predict charging finish times and make optimal scheduling decisions. The use of these algorithms in conjunction with ToU tariffs is cost effective when compared to flat rate tariffs. Grid load analysis shows that scheduling according to time lowers peak demand, equalizes load distribution, and lowers operating costs. A quantitative comparison has demonstrated both grid stability and economic efficiency gains over uncontrolled charging. The result is an extremely flexible framework for different charging events or stations which will be a viable way of managing energy in the fast-growing EV charging networks.