AI-Driven Digital Twins for Enhancing Indoor Environmental Quality and Energy Efficiency in Smart Building Systems

Smart buildings equipped with diverse control systems serve the objectives of gathering data, optimizing energy efficiency (EE), and detecting and diagnosing faults, particularly in the domain of indoor environmental quality (IEQ). Digital twins (DTs) offering an environmentally sustainable solution for managing facilities and incorporated with artificial intelligence (AI) create opportunities for maintaining IEQ and optimizing EE. The purpose of this study is to assess the impact of AI-driven DTs on enhancing IEQ and EE in smart building systems (SBS). A scoping review was performed to establish the theoretical background about DTs, AI, IEQ, and SBS, semi-structured interviews were conducted with the specialists in the industry to obtain qualitative data, and quantitative data were gathered via a computerized self-administered questionnaire (CSAQ) survey, focusing on how DTs can improve IEQ and EE in SBS. The results indicate that the AI-driven DT enhances occupants’ comfort and energy-efficiency performance and enables decision-making on automatic fault detection and maintenance conditioning to improve buildings’ serviceability and IEQ in real time, in response to the key industrial needs in building energy management systems (BEMS) and interrogative and predictive analytics for maintenance. The integration of AI with DT presents a transformative approach to improving IEQ and EE in SBS. The practical implications of this advancement span across design, construction, AI, and policy domains, offering significant opportunities and challenges that need to be carefully considered.