Autoregressive Models for Solving the Problem of Forecasting Active Energy Complexes

Abstract

This paper solves the problem of forecasting active energy complexes using autoregressive models. Forecasting in the energy business is one of the common tasks these days. Nowadays, forecasting helps with long-term strategic planning. However, different application fields and the duration of the forecast sometimes require a radically different approach, and there is no universal model and method that can equally effectively predict any result set. In this research paper, the implementation and analysis of 4 models are introduced: Simple Autoregressive Models (AR), Moving Average Models (MAq), Autoregressive Integrated Moving Average Models (ARIMA), and Seasonal AutoRegressive Integrated and Moving Average Models (SARIMA).