Key points are not available for this paper at this time.
With the rapid advancement of machine learning (ML) technologies, their innovative applications in enhancing building energy efficiency are increasingly prominent. Utilizing tools such as VOSviewer and Bibliometrix, this study systematically reviews the body of the related literature, focusing on the key applications and emerging trends of cutting-edge ML techniques, including deep learning, reinforcement learning, and unsupervised learning, in optimizing building energy performance and managing carbon emissions. First, this paper delves into the role of ML in building performance prediction, intelligent energy management, and sustainable design, with particular emphasis on how smart building systems leverage real-time data analysis and prediction to optimize energy usage and significantly reduce carbon emissions dynamically. Second, this study summarizes the technological evolution and future trends of ML in the building sector and identifies critical challenges faced by the field. The findings provide a technology-driven perspective for advancing sustainability in the construction industry and offer valuable insights for future research directions.
Liu et al. (Fri,) studied this question.