Regression Machine Learning of an Hourly Model of National Electric Power Demand System

The article shows that it is possible to use the regression machine learning method arx to obtain a parametric ARX model of the National Electric Power Demand System with high quality and accuracy, and on this basis also to obtain models of SS state variables, which required, among others: designing a method of using available data, performing machine learning on selected examples, transforming models from ARX models to SS state variable models, evaluating the obtained models using simulation models, attempting to interpret the obtained research results, etc. The research was carried out in the MATLAB and Simulink environment using real values related to the production and consumption of electricity of the National Power System.