Stacked Ensemble Machine Learning Model of Energy Consumption Prediction

The need for energy has significantly increased in recent decades as a result of rapid urbanization, excessive energy consumption and population growth. This leads to environmental problems such as climate change, water and air pollution. Predicting energy consumption can reduce these problems and helps energy management and efficacity. In this paper, we investigate the performance of several machine learning methods, such as linear regression, K-Nearest neighbor, support vector regressor, random forest, gradient boosting, and stacking to predict energy consumption in Tetouan city, in Morocco. To evaluate the performance of these models, evaluation metrics such as MAE, RMSE, and R2 were used. Stacking method provided outstanding performance and the best result with accuracy of 98.13%, 98.11% and 99.05% in zone 1, 2, 3, respectively.