Optimisation of occupant comfort and energy consumption in Indoor environments: Responsive homes through Digital Twin and building automation integration

Purpose: Building Automation System (BAS) presents encouraging opportunities to optimise energy consumption while elevating occupants’ thermal comfort. BAS ranges from regular thermostatic valves to home automation systems (HAS), in residential buildings. Well-designed HAS advantage in occupant spaces, providing optimum occupant comfort and energy efficiency. However, not accompanying essential parameters such as real-time climate conditions and occupancy thermal behaviour prevent real-time responsive HAS developments. Existing studies demonstrate an elevated need for efficient HAS, which can potentially consider these significant influencing factors with real-time responses. A developed approach that considers these dynamic changes provides an accurate HAS that addresses the current performance gap. Research Design: Digital Twin (DT) serves as a core platform for real-time monitoring and control of the building, it enables automated controls to adjust Heating Ventilation Air Conditioning (HVAC) systems and other services to enhance occupants’ comforts by integrating with the BAS. Therefore, this study explores the opportunities for integrating Digital Twin technology into the HAS to create more human-centric indoor environment conditions while reducing the energy performance gap in home energy management systems. Therefore, this study aims to develop a Home Automation System using AI (AI), Machine Learning (ML), and Digital Twin (DT). Outcome: High-responsive home automation system using AI, ML, and DT. Contribution: The findings of this study contribute to developing high responsive BAS through AI, ML, and DT.