Emedo, Chinwe, Wada, Ojima Z., David-Olawade, Aanuoluwapo Clement, Ling, Jonathan, Esan, Deborah T., Ijiwade, James and Olawade, David ORCID: https://orcid.org/0000-0003-0188-9836 (2025) AI-Driven Transformations in Smart Buildings: A Review of Energy Efficiency and Sustainable Operations. Digital Engineering. p. 100068. (In Press)

Full text not available from this repository.

Abstract

This comprehensive review examines the transformative impact of artificial intelligence (AI) technologies on smart buildings and real estate management through a systematic narrative analysis of peer-reviewed articles and industry reports published between 2016-2024. Using a thematic synthesis approach across five primary domains, property valuation, predictive maintenance, tenant screening, marketing and sales, and smart building operations, we investigated AI's role in enhancing energy efficiency and sustainable operations. Key findings reveal that AI-powered systems achieve remarkable performance improvements: valuation accuracy increased from 70% to 95%, operational costs reduced by 17.6%, maintenance costs decreased by 13.2%, and energy savings reached 14% while maintaining 91% resident satisfaction. Our analysis identifies critical implementation barriers including data quality challenges, algorithmic bias risks, substantial upfront investments, and skills gaps. The review reveals that ensemble machine learning techniques achieve 85-100% accuracy in energy forecasting, while IoT-integrated predictive maintenance systems extend equipment lifespan by 25-30%. Despite promising benefits, ethical considerations around privacy, transparency, and fairness demand immediate attention. This review contributes novel insights into the economic-environmental nexus of AI adoption, demonstrating that sustainable building operations and profitability are not mutually exclusive but rather synergistic outcomes of intelligent system integration.

Item Type:	Article
Status:	In Press
DOI:	10.1016/j.dte.2025.100068
School/Department:	London Campus
URI:	https://ray.yorksj.ac.uk/id/eprint/12826

University Staff: Request a correction | RaY Editors: Update this record