Modelling and prediction of energy efficient building climate toward digital twin integration

Buildings account for a significant share of energy usage on a global scale, with heating, ventilation, and air conditioning (HVAC) systems being the main energy consumers. Building energy management (BEM) is a critical field that focuses on optimizing energy consumption and improving efficiency within commercial structures. Achieving precise indoor temperature prediction and regulation is crucial for enhancing building thermal performance and optimizing thermal energy utilization. Accurately pinpointing the influential parameters and factors is essential to devise an advanced building control system capable of effectively regulating indoor temperature, optimizing thermal energy usage, and improving the overall thermal performance of occupants. The integration of sensor data, internet of thing (IoT) devices, communication protocols, real-time simulations, machine learning, and visualization intelligence creates a digital twin (DT) model of systems. Through the DT model, systems can be dynamically represented and analysed, offering valuable insights for monitoring, optimization, and decision-making. This research analyses the thermal energy performance of a specific zone in the N79 building at Griffith University during the summer season, using sensor data from the BEM system. The objective is to gain insights into energy consumption patterns, temperature regulation, and overall efficiency of the zone, contributing to a better understanding of thermal energy management in the building.