Collecting building occupancy data of high resolution based on WiFi and BLE network

Building occupancy information is the premise of modern building service systems' control and energy conservation. Inaccurate occupancy information could result in a low comfort level and an energy waste. Existing occupancy detecting system relies on indirect and low-resolution environmental sensors, which potentially mislead facility managers and result in inefficiency in building energy use. In this study, the authors proposed a novel occupancy detection approach through a coupled indoor positioning system. The system integrates conventional k-nearest neighbor positioning algorithm and stochastic random walk algorithm to collect high-resolution occupancy data through Wi-Fi and Bluetooth Low Energy (BLE) networks. The proposed system is able to identify the meshed geospatial distribution of occupants, and to future track their movements in a network covered space. The detected occupancy meshes are suitable for direct implementation in building facility management since their operation is based on thermal zones rather than occupants' coordinates. To validate the feasibility and accuracy of the proposed system, the authors conducted a preliminary experiment in an institutional building. By comparing the positioning distance measurement metrics and matching parameters, the authors found the occupancy information detected by the proposed model is highly precise, accurate and reliable for the application in the building energy management.