Applications and Trends of Machine Learning in Building Energy Optimization: A Bibliometric Analysis

• Published in: Buildings (Basel) Vol. 15; no. 7; p. 994
• Main Authors: Liu, Jingyi, Chen, Jianfei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 21.03.2025
• Subjects: Architecture and energy conservation; bibliometric analysis; Bibliometrics; building energy efficiency; Carbon; Construction industry; Data analysis; Data collection; Deep learning; Emissions; Emissions (Pollution); Energy consumption; Energy efficiency; Energy management; energy optimization in buildings; Energy usage; Forecasts and trends; Green buildings; Green design; Learning algorithms; Literature reviews; Machine learning; machine learning (ML); Optimization; Performance prediction; Real time; Scientometrics; Sustainability; Sustainable design; Sustainable development; Trends; Unsupervised learning; Australia; United States; China
• ISSN: 2075-5309; 2075-5309
• DOI: 10.3390/buildings15070994

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.