Key points are not available for this paper at this time.
Smart buildings play a vital role in achieving sustainable urban transformation by providing safe, efficient, and low-carbon environments. As global decarbonization targets intensify, net-zero energy buildings (NZEBs) are increasingly recognized as a pathway to balance energy demand and renewable generation. Towards this direction, digital twins (DTs), virtual replicas that incorporate multi-source data, simulation, and control, have become indispensable for optimizing building performance and facilitating grid-connected energy management. This study investigates the role of DTs in supporting digital transformation for NZEBs, focusing on their integration with optimization, machine learning (ML), and artificial intelligence (AI) for intelligent decision-making. The proposed framework encompasses offline optimization for design calibration, online optimization for real-time adaptive control, and federated optimization for secure, distributed collaboration among multiple smart buildings. The review emphasizes the significance of key enablers, including data interoperability, human–machine interaction, predictive maintenance, and real-time monitoring, in improving system reliability and user engagement. The findings indicate that DTs improve energy forecasting, demand response, and occupant comfort, contributing to reduced environmental impact and improved operational efficiency. By bridging the physical and virtual layers of the built environment, DT establishes a foundation for self-optimizing, resilient, and data-driven NZEBs. It represents a transformative advancement in achieving net-zero energy performance, intelligent control, and sustainable building-grid integration, offering a pivotal step toward the next generation of smart and carbon-neutral built environments.
Hannan et al. (Wed,) studied this question.