Model for Forecasting the Volume of Electricity Consumption Using the «Random Forest» Algorithm

The article presents the peculiarities of applying the Random Forest (RF) algorithm for short-term forecasting of electricity consumption by consumers served by a supplier company. As a result of processing historical data using the RF algorithm, a forecasting model was developed that takes into account time, meteorological, and calendar features. Identification of the mo-del’s hyperparameters made it possible to achieve high accuracy in forecast calculations. The results of the experimental calculations demonstrate the effectiveness of the model, in particu-lar, the possibility of finding its key qualifying parameters. The features of the model applica-tion in the decision-making system of the supplier company regarding the management of en-ergy resources and minimization of the imbalance of electricity volumes in the market are shown.