Digital Twin Insights from a Green Star-Rated Learning Environment

This study investigates the application of digital twin technology to enhance energy efficiency and indoor environmental quality (IEQ) in a Green Star-rated learning environment. Focusing on Nelson Mandela University’s Business School, the research employed a mono-method quantitative approach, gathering real-time data through IoT sensors. The sensors were integrated into a digital twin platform using AWS IoT TwinMaker, enabling multi-sensor collaborative visualisation of building performance data. Findings reveal that CO₂ levels frequently exceeded recommended limits, even at moderate occupancy, indicating ventilation inadequacies. Additionally, the performance gap between design expectations and operational outcomes was highlighted, especially regarding energy efficiency and IEQ, suggesting a need for more responsive building systems. Analysis of venue utilisation showed patterns of underuse, particularly on weekends, presenting an opportunity for optimising HVAC and lighting schedules to align with actual occupancy trends. The study demonstrates the potential of digital twins for real-time monitoring and data-driven decision-making, offering actionable insights to bridge the performance gap and improve sustainability in educational facilities. Future research could expand on these findings by exploring AI integration for predictive maintenance and enhanced energy management, further advancing the role of digital twins in sustainable building practices.