Occupancy monitoring using environmental and context sensors and a hierarchical analysis framework

Saving energy in residential and commercial buildings is of great interest due to diminishing resources. Heating ventilation and air conditioning systems, and electric lighting are responsible for a significant share of energy usage, which makes it desirable to optimise their operations while maintaining user comfort. Such optimisation requires accurate occupancy estimations. In contrast to current, often invasive or unreliable methods we present an approach for accurate occupancy estimation using a wireless sensor network (WSN) that only collects non-sensitive data and a novel, hierarchical analysis method. We integrate potentially uncertain contextual information to produce occupancy estimates at different levels of granularity and provide confidence measures for effective building management. We evaluate our framework in real-world deployments and demonstrate its effectiveness and accuracy for occupancy monitoring in both low- and high-traffic area scenarios. Furthermore, we show how the system is used for analysing historical data and identify effective room misuse and thus a potential for energy saving.