| Buildings account for a significant portion of global energy consumption. Improving their energy performance is crucial for achieving energy efficien-cy and sustainability goals. Heating and Cooling load (HCL) indices are among the most significant contributors towards this target. Accurate predic-tion of HCL is crucial for designing energy-efficient buildings, for optimiz-ing their operations, and reducing respective energy costs. This research in-vestigates the development and use of trustworthy Machine Learning (ML) models towards the aforementioned targets. The datasets considered were obtained from the literature, based on simulated buildings’ models. Data preprocessing was performed to derive meaningful features for regression modeling. The predictive power of various ML algorithms was evaluated, and the determination of the optimal model was based on a detailed compar-ative analysis. The findings of this research provide insights into the effec-tiveness of Artificial Intelligence (AI) models in predicting heating and cool-ing loads and they can motivate the development of more accurate and effi-cient energy management systems for buildings. Building owners can identi-fy energy-saving opportunities, and they can reach informed decisions about energy efficiency measures that can reduce energy costs. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.