Adaptive Ensemble Learning for Enhancing Building Energy Consumption Prediction: Insights from COVID-19 Pandemic Energy Consumption Dynamics

Buildings account for approximately 40% of the total global energy consumption. Therefore, accurate prediction of building energy consumption is necessary to optimize resource allocation and promote sustainable energy usage. A key challenge in developing building energy consumption models is their adaptability to abrupt changes in consumption patterns owing to extraordinary events, such as the COVID-19 pandemic. Therefore, a two-layer ensemble-learning (EL) model incorporating sliding windows as input features is proposed. The model is a two-layer stacking EL consisting of two base learning methods: (1) support vector regression (SVR), and (2) random forest (RF). Temperature and humidity are included to account for the influence of weather conditions on energy consumption. The proposed model is deployed to forecast building energy consumption both before (November 2019) and during (May – October 2020) the COVID-19 pandemic and is compared with a single machine learning model. The results demonstrate that the EL model outperforms the SVR and RF methods, providing excellent prediction accuracy even during the pandemic when significant changes in energy consumption patterns occurred. The findings also highlight the effectiveness of sliding windows as input features for improving model adaptability. Additionally, the analysis reveals that temperature is more prominent than humidity for improving prediction accuracy.