A Taxonomy for Low Computational Complexity of Energy Optimization in Smart Building

The growing energy demand and the need for sustainable solutions have led to the rise of smart buildings equipped with innovative technologies aimed at optimizing energy use. Machine learning (ML) algorithms play a pivotal role in these buildings by predicting energy consumption trends, detecting anomalies, and automating control systems. This review provides a thorough analysis of the most advanced machine learning algorithms used for energy optimization, while also offering a new perspective by categorizing these algorithms based on their commercial viability, computational efficiency, and applicability to different building types. Additionally, the paper synthesizes recent progress and highlights key research gaps, offering practical recommendations for future investigations.