Driving Sustainable Smart Buildings through Federated Intelligence and Digital Twin Integration

Abstract

Intelligent system technology has played a vital role in the design of sustainable smart buildings that strive to ensure energy efficiency while retaining occupant comfort. The current study offers an integrated framework that combines federated learning with digital twin for privacy-preserving and scalable building management. Federated LSTM is used to perform predictions on occupancy in distributed systems without revealing any data to preserve data privacy. A digital twin of the building is constructed to simulate occupancy and energy consumption in order to make decisions about how to control the building. The occupancy-driven energy optimization technique is utilized to control the HVAC and lighting systems smartly. The experimental results indicate that our framework not only yields accurate predictions but also shows stable results in terms of energy consumption and carbon emissions. The findings highlight the effectiveness of integrating federated intelligence with digital twins in enabling efficient, scalable, and sustainability-driven smart building solutions. This work contributes toward next-generation intelligent infrastructure by providing a robust and privacy-aware approach to energy-efficient building management.