Modeling and predicting the occupancy in a China hub airport terminal using Wi-Fi data

The research on building energy consumption of airport terminal is of great importance, especially considering the rapid development of civil aviation in China. One of the key elements influencing the building energy consumption is the occupancy. This paper proposes an occupancy model based on dwell time distribution and applies it to the data set acquired through the Wi-Fi indoor positioning system. Firstly, this paper briefly describes the passenger flow in a Chinese hub airport terminal in 66 days. On this basis, the distribution of passengers' dwell time, averaging at 96.97 min but varies with time, airlines or delay, is extracted and modeled through a Bayesian method. Furthermore, the occupancy is effectively predicted in high spatial-temporal resolution based on the flight schedule and the model before, reaching a 0.747 r-square. The new data source and mathematical model will be instructive in future occupancy research, and the prediction model will benefit the optimization of the operational strategy of terminal buildings. (C) 2019 Elsevier B.V. All rights reserved.