A Non-Intrusive Occupancy Monitoring System for Demand Driven HVAC Operations

In the U.S., 40% of the energy consumption is from buildings, approximately 48% of which is consumed by heating, ventilation, and air conditioning (HVAC) systems. Implementing demand driven HVAC operations is a way to reduce HVAC related energy consumption, and ultimately to achieve sustainable building operations and maintenance. This relies on the availability of occupancy information, which determines peak/off-hour modes and impacts cooling/heating loads of HVAC systems. This research proposes an occupancy monitoring system that is built on a combination of non-intrusive sensors that can detect indoor temperature, humidity, CO2 concentration, door status, light, sound and motion. The effectiveness of each sensor in occupancy estimation is evaluated. The sensor data is communicated wirelessly, and processed in real time using a back-propagation (BP) artificial neural network (ANN) algorithm. Field tests are carried out in a lab space that is shared by up to 9 people for 15 consecutive days. The test results report an overall detection rate of over 90%, which indicates the ability of the proposed system to monitor the occupancy information of multi-occupancy spaces in real time in support of demand driven HVAC operations.