Лінійні моделі для прогнозування навантаження електричної мережі гідроелектростанції

Abstract

This work will focus on the use of machine learning methods for planning the stability of power grids. We will consider autoregression for predicting future voltage values based on historical data alone, and more general linear regression for finding the relationship between various weather indicators and transformer voltages. The data to be used for forecasting includes observations from meteorological stations located in the service area of the hydropower plant: temperature, wind speed, cloud cover and precipitation, as well as voltage values at the transformers of the power plant.