Bootstrap aggregating approach to short-term load forecasting using meteorological parameters for demand side management in the North-Eastern Region of India

Electricity is an essential commodity that must be generated in response to demand. Hydroelectric power plants, fossil fuels, nuclear energy, and wind energy are just a few examples of sources significantly impact production costs. Accurate load forecasting for specific region would allow more efficient management, planning, scheduling low-cost generation units ensuring on-time delivery full monetary benefit. Machine learning methods becoming effective on grids as data availability increases. Ensemble models hybrid algorithms combine various machine intelligently incorporate them into single predictive model reduce uncertainty bias. In this study, several ensemble were implemented tested short-term electric forecasting. The suggested method trained using the influential meteorological variables obtained through correlation analysis past load. We used real-time from Nagaland’s dispatch centre India parameters Nagaland analysis. synthetic minority over-sampling technique regression (SMOTE-R) also employed avoid imbalance issues. experimental results show Bagging outperform other with respect mean squared error absolute percentage error.