This study investigates the use of digital twin technology, machine learning (ML), and artificial intelligence (AI) to improve energy efficiency. It focuses on the heating, ventilation and air conditioning (HVAC) systems in hotel buildings which rely on central air-conditioning 24/7 throughout the year for ensuring thermal comfort and air ventilation. We develop a three-phase digital twin framework illustrating the progression from monitoring to autonomous control. Using data from real-world deployment in a Hong Kong hotel since 2013, we evaluated the evolution of digital twin applications from the Fixed Mode, to the Energy Optimisation Solution (EOS) Mode, finally to an AI-driven autonomous system. Leveraging 17,520 hourly data points from 1416 Internet of Things sensors, we relate digital twin features to environmental benefits based on energy consumption and Energy Efficiency Ratio (EER). For energy consumption, the AI Mode achieves the lowest daily energy consumption, averaging 841.94 kWh, which was 21.91% lower than Fixed mode and 50.42% lower than EOS mode. Under real-world conditions, the AI-driven autonomous digital twin improved EER by 6.2% over EOS and 2.9% over the Fixed Mode, confirming its superior thermal efficiency. The results demonstrate the benefits of combining digital twins with AI to enable intelligent, scalable, and energy-efficient buildings.
Becky P.Y. Loo (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: