Machine Learning-Based Strategy for the Regulated Charging of Plug-In Electric Vehicles

Plug-in electric vehicles (PEVs) are a practical and environmentally friendly substitute for conventional automobiles. PEVs have great potential to reduce greenhouse gas emissions by utilizing electricity as their primary energy source, thereby mitigating the negative environmental effects of traditional transportation systems. However, due to the increased and frequently irregular demand for charging, the growing integration of PEVs into the electrical grid raises significant concerns regarding operational dependability and grid stability. In addition to increasing higher charging prices and perhaps causing infrastructure stress, random charging could place further strain on the distribution network. To cope with this issue, this paper proposes a controlled charging approach with centralized control architecture to regulate and schedule the charging process of PEVs powered by machine learning techniques such as neural networks and Naive Bayes, to minimize charging costs. Simulation results demonstrate the efficacy of this strategy, showing cost savings of around 50% and 36% in comparison to the random charging process.