Conference Year



Occupancy modelling, Occupancy prediction, Energy efficiency, Building occupancy, Occupancy-driven control


The primary energy consumer of smart buildings are Heating, Ventilation, and Air-Conditioning (HVAC) systems, approximately 30% of the building energy use, which usually operate on a fixed schedule. Currently, most modern buildings still condition rooms with a set-point assuming maximum occupancy rather than actual usage. As a result, rooms are often over-conditioned needlessly. Occupancy-based controls can achieve significant energy savings by temporally matching the building energy consumption and building usage, conservative user behavior can save a third of expended energy.  In this paper, we present a simple yet effective algorithm to automatically assign reference temperature set-points based on the occupancy information. Both the binary and detailed occupancy estimation cases are considered. In the first case study, we assume the schedule involves only binary states (occupied or not occupied), i.e. the room is invariant. With long-term observations occupancy levels can be estimated using statistical tools. In the second case study, three techniques are introduced. Firstly, we propose an identification-based approaches. More precisely, we identify the models via Expectation Maximization (EM) approach. The statistical state space model is built in linear form for the mapping between the occupancy measurements and real occupancy states with noise considered. Secondly, we propose a method based on uncertain basis functions for modeling and prediction purposes. In literature, basis functions (e.g., radial basis functions, wavelets) are fixed; instead, we assume that the basis functions are random. We consider basis functions with three different distributions, which are Gaussian, Laplace and Uniform, respectively. Finally, we introduce a novel finite state automata (FSA) which is successfully reconstructed by general systems problem solver (GSPS). As far as we know, no studies have used the finite state machine or general system theory to estimate occupancy in buildings. All above estimates can be used to adaptively update the temperature set-points for HVAC control strategy.  To demonstrate effectiveness of proposed approach, a simulation-based experimental analysis is carried out using occupancy data. We define the estimation accuracy as the total number of correct estimations divided by the total number of estimations, and both Root Mean Squared Error (RMSE) and estimation accuracy analysis are provided. All the proposed estimation techniques could achieve at least 70% accuracy rate. Generally, accuracy for binary states estimation is much higher than that of detailed occupancy. For GSPS model, more training data improves performance of estimation. It should be remarked that although some mismatch exist for non-zero jumps, estimation performance tracks the zero base line (non-occupied status) perfectly. Therefore, the estimation techniques are effective for binary estimation with over 90% accuracy. Finally, the estimated occupancy is applied into temperature set algorithm to generate reference temperature curve. By adjusting temperature set curve, we can achieve significant energy without sacrificing customer’s comfort.  In this paper, we propose three real-time occupancy estimation methods that can be incorporated into HVAC controls . We have shown the effectiveness of all the proposed approaches by simulation examples. We have seen great potential of energy saving by integrating the proposed technique into real HVAC control system.    Â