Data driven machine learning models for short‐term load forecasting considering electrical vehicle load

Abstract Electric vehicles (EVs) are gaining popularity due to their fuel efficiency and ability reduce greenhouse gas emissions. Significant penetration of EVs with unregulated charging, which can have a substantial impact on power networks. Accurate load predictions, including the charging crucial for ensuring cost‐effective dependable operation systems. In order estimate short‐term in presence EV load, XG (extreme gradient) boost algorithm is proposed effectiveness performances checked against other models. A variety distinct meteorological parameters electrical pattern years 2017 2018 Northeast India used train machine learning classifier R ‐squared value analyses also performed identify most correlated input that influence results various Analysis shows temperature, cloud cover, heat index, dew point, wind chill, perceived temperature substantially connected electricity consumption. The performance outperformed by comparing prediction decision tree, random forest, K nearest neighbors, logistic regression. Three separate case studies were employed verification using precision, F1 score, sensitivity, specificity, accuracy metrics. Our findings demonstrate that, comparison forecasting models, Boost exhibits higher (83.84%, 81.51%, 85.97%) robust forecasts.