ABSTRACT: The COVID-19 pandemic has recently brought IAQ upfront and will play a crucial role in minimising the transmission of viruses suggesting to increase the outdoor ventilation however, this could create poor temperature and humidity in some buildings, affecting the comfort and health of occupants. This causes unnecessary energy consumption and wastage and compromises the HVAC efficiency. This is further exacerbated when the ventilation system is operated using fixed or static schedules and when spaces are partially occupied or unoccupied for significant periods, leading to unnecessary over-ventilation and -conditioning of spaces. A potential solution is the use of demand-driven or occupant centric control measures, such as demand-controlled ventilation (DCV) which varies the ventilation of a space according to the pollution level or occupancy. The present study investigated the potential of applying a live occupancy detection approach to assist demand-driven heating, ventilation, and air-conditioning (HVAC) systems to ensure adequate indoor thermal conditions and air quality were achieved while reducing unnecessary building energy loads to improve building energy performance. Faster region-based convolutional neural network (RCNN) models were trained to detect the number of people and occupancy activities respectively and deployed to an AI-powered camera. Experimental tests were carried out within the case study room to assess the performance of this approach. The count-based occupancy deep learning profiles were produced during the detection according to the real-time information about the number of people and their activities. To estimate the effect of this approach on indoor air quality and ventilation energy demand, scenario-based modelling of the case study building under four ventilation strategies was carried out via building energy simulation (BES). Results showed that the proposed approach could provide demand-driven ventilation controls based on dynamic changes of occupancy to improve the indoor air quality (IAQ) and address the problem of under or over-estimation of the ventilation energy consumption when using the static or fixed profiles.
 

artificial intelligence, buildings, HVAC, modelling, ventilation