Development of Machine Learning Based Daily Peak Load Forecasting System for Winter Season in the State of Meghalaya in India

Load forecasting is a technique used by power companies to predict the energy needed to balance the supply and load demand at all times. It is also a mandatory requirement for proper functioning of the electrical power supply industry. Load forecasting is critical to provide decision-making support for power generation. An accurate load forecasting can ensure sufficient power being generated to fulfill actual need of the community and reduce waste of generation. In this paper, a regression-based method is presented for load forecasting in Meghalaya. The efficiency of the methodology is evaluated on the dataset and the predicted values are compared with the actual maximum load demands. The method is found to be effective in accurately forecasting of maximum load demand during the winter season in Meghalaya. This method can be applied to any place in the world having colder climate, with load dependency on heating elements, especially during the winter season.