Прогнозування навантаження трансформаторів електричної мережі методами машинного навчання

Abstract

This research will focus on the application of machine learning techniques to develop a strategy for the stability of electric power grids. Autoregression is investigated to predict future voltage levels based solely on past data, and the issue of seasonality in the dataset is explored. The dataset used for the predictive analysis includes data collected from meteorological stations within the operating range of the hydropower plant, including temperature, wind speed, cloud cover, precipitation, and transformer voltage readings.