Abstract
Electric vehicle (EV) consumers are drawn to the convenience of charging their vehicles at home because of their low operating costs and pollution-free technology. Additionally, EV customers have limited availability of charging stations on the road. The integration of EVs into Internet of Things-enabled smart homes presents a promising avenue for optimizing green energy usage and reducing charging costs. This paper proposes an innovative framework for optimized EV charging management using artificial neural network (ANN)-based forecasting and intelligent scheduling of available clean energy and load demand. The problem may be effectively addressed, when intelligent EV routing is integrated with smart home station charging time scheduling. ANN models are designed to predict future energy demand and renewable energy availability, enabling proactive and efficient decision-making. An intelligent scheduling algorithm dynamically allocates charging periods based on forecasted data, prioritizing low-cost, renewable energy sources while ensuring user-defined constraints and meeting demand and supply deadlines effectively. In this context, the ANN model has been designed to anticipate demand and energy for a solar-based home charging station. The results demonstrate significant improvements in energy efficiency, cost savings, and system sustainability compared to traditional charging methods.

This publication has 25 references indexed in Scilit: