Developing a residential occupancy schedule generator based on smart thermostat data

Abstract

Occupancy patterns play a major role in residential buildings’ energy demand. This role is essential to be represented realistically in urban-scale energy simulations with a focus on matching the supply of renewable energy to demand. However, the lack of large-scale datasets that represent the seasonality and dynamic nature of occupancy, especially within the residential sector limited such analysis. Recently, the fast adoption of smart thermostats, featuring passive infrared sensors for motion detection, in residential buildings has allowed for extracting more representative occupancy information for different applications. To this end, this study introduces an open-source Python package to generate large-scale hourly occupancy profiles for residential buildings based on smart thermostat readings. The package takes advantage of the Donate Your Data (DYD) dataset by Ecobee to develop a rule-based framework that addresses the limitations of relying on motion-detection data to represent the whole-building occupancy. The framework was applied to over 8000 Canadian households as a case study. The generated profiles for these buildings are validated by comparing them with residential occupancy profiles generated from the Canadian Time Use Survey (TUS). The results showed that both profiles were statistically similar with a 3 % difference in the aggregated daily occupied hours. Finally, the diversity of the generated profiles before and after the COVID-19 pandemic is investigated to demonstrate the usefulness of the tool. The results proved the potential of the developed package to generate realistic and diverse occupancy schedules for the residential sector.