ODE, regression, and ANN models for energy forecasting: Egypt as a study case

Abstract

Energy plays a crucial role in national development, influencing critical sectors such as industry, agriculture, healthcare, and education. Accurate energy consumption prediction is essential for efficient energy management, helping prevent imbalances between supply and demand and potential energy shortages. This study aims to forecast the total primary energy supply (TPES), using Egypt as a case study for the first time in literature and utilizing several models (ordinary differential equations (ODEs), regression, and ANN models). Although ordinary differential equations (ODEs) offer flexibility and convenience, their application in energy forecasting remains limited. One of the main objectives of this research is to evaluate the effectiveness of ODEs in predicting energy consumption. Various ODE and regression models are employed to identify the most suitable model amongst each category for forecasting energy demand. Additionally, an artificial neural network (ANN) is developed, trained, validated, and tested for the same forecasting task. The study compares the performance of the selected ODE model (Mendelsohn), with the selected regression model (Polynomial), and an ANN model predicting Egypt’s TPES until 2035. By assessing multiple forecasting methods, this work improves the accuracy and reliability of energy consumption predictions, which is crucial for sustainable energy planning and policy development.