Digital Twin of HVAC system (HVACDT) for multiobjective optimization of energy consumption and thermal comfort based on BIM framework with ANN-MOGA

This study proposes a novel Digital Twin framework of heating, ventilation, and air conditioning (HVACDT) system to reduce energy consumption while increasing thermal comfort. The framework is developed to help the facility managers better understand the building operation to enhance the HVAC system function. The Digital Twin framework is based on Building Information Modelling (BIM) combined with a newly created plug-in to receive real-time sensor data as well as thermal comfort and optimization process through Matlab programming. In order to determine if the suggested framework is practical, data were collected from a Norwegian office building between August 2019 and October 2021 and used to test the framework. An artificial neural network (ANN) in a Simulink model and a multiobjective genetic algorithm (MOGA) are then used to improve the HVAC system. The HVAC system is comprised of air distributors, cooling units, heating units, pressure regulators, valves, air gates, and fans, among other components. In this context, several characteristics, such as temperatures, pressure, airflow, cooling and heating operation control, and other factors are considered as decision variables. In order to determine objective functions, the predicted percentage of dissatisfied (PPD) and the HVAC energy usage are both calculated. As a result, ANN's decision variables and objective function correlated well. Furthermore, MOGA presents different design factors that can be used to obtain the best possible solution in terms of thermal comfort and energy usage. The results show that the average cooling energy savings for four days in summer is roughly 13.2%, and 10.8% for the three summer months (June, July, and August), keeping the PPD under 10%. Finally, compared to traditional approaches, the HVACDT framework displays a higher level of automation in terms of data management.