Functioning of an Intelligent System on the Example of the National Power Demand System

Abstract

This publication includes a concept and research results regarding the search for regularity in the functioning of an intelligent system using the example of a system for forecasting national power demand. The research employs the ARX regression machine learning method to derive models of the functioning of the electricity forecasting system. The study uses actual values of electricity generated by both uniform and non-uniform domestic electricity systems as input quantities, and forecasted national power demand as the output values from January 2023. The main aim of the research was to obtain several hourly models and several monthly models to demonstrate changes in selected system parameters and to show whether, and what changes occur in the direction of increasing the system’s independence, enhancing the system control level, etc. The research methodology also employs, in addition to the machine learning method, the method of control theory and systems. At the same time, an example of obtaining a model of the national system demand for electric power using the ARX machine learning method, which was transformed into state space model, whose matrix elements were used to interpret the correctness of changes in the intelligent system.