Energy management of smart buildings during crises and digital twins as an optimisation tool for sustainable urban environment

The COVID-19 pandemic underscored the need for resilient energy management systems in smart buildings, especially during crises. This study investigates the role of Digital Twins in optimising energy systems, analysing energy use in a residential complex in Cyprus under lockdown conditions. Advanced predictive models, including Skforecast, XGBoost, LightGBM, CatBoost, LSTM, and RNN, were employed to forecast energy demand. While gradient boosting models performed well, LSTM showed superior accuracy in capturing long-term patterns. These models are crucial for anticipating energy demand fluctuations, especially during unforeseen events such as the COVID-19 pandemic. The use of Digital Twins enabled real-time monitoring, proactive maintenance, and decision-making, significantly improving energy efficiency and resilience. This research underscores the importance of interdisciplinary collaboration and the integration of advanced technologies in building management. The findings advocate for a holistic, human-centric approach to energy management that prioritises adaptability, resilience, and sustainability in the face of ongoing and future challenges.