Comparative Study of Machine Learning Techniques to Forecast Electricity Demand and Supply in Iraq
TL;DR
A machine learning-based predictor of power consumption, i.e., random forest, XGBoost, linear regression for power forecasting, is introduced and the best performance model for demand was XGBoost and the best performance model for supply was XGBoost.
Abstract
Accurate forecast of electricity demand has become essential for modern energy systems, which are Face-off escalating challenges because of industrial expansion, population growth, and the incorporation of renewable energy sources. With the development of machine learning methods, one can now efficiently forecast power consumption with the help of past data. This paper introduces a machine learning-based predictor of power consumption. We analyze various machine learning techniques, i.e., random forest, XGBoost, linear regression for power forecasting, in this work. These models were trained and tested on historical electricity consumption data from the Ministry of Electricity of Iraq, 2022 to 2025. The models' performance was evaluated using a number of metrics, such as Mean Absolute Error, Root Mean Squared Error, Mean absolute percentage error, and R-squared. the best performance model for demand was XGBoost, the model achieved on R-squared value of 0.98 and Linear regression model achieved on R-squared value of 0.98 for supply.