A three-year dataset supporting research on building energy management and occupancy analytics
Abstract
"A high-resolution, three-year dataset from a real office building, integrating whole-building/end-use energy consumption, HVAC system data, environmental parameters, and ground-truth occupant counts. Essential for research in smart building energy prediction, optimization, and occupancy analytics."
Description
This comprehensive dataset was curated to support advanced research in smart building energy management. It captures the complex interplay between energy use, building systems, and human occupancy in a medium-sized office building constructed in 2015.
Key Features & Applications:
- Data Richness: Over 300 sensors collected data on electricity consumption (whole-building and end-use), HVAC operating conditions, indoor/outdoor temperatures, and precise occupant counts via cameras and WiFi proxies[citation:7].
- Temporal Scope: Includes two years of pre-pandemic operation (2018-2019) and one year impacted by COVID-19 (2020), offering unique insights into pandemic effects on building energy patterns[citation:7].
- Research Applications: Designed for building energy benchmarking, load shape analysis, energy and occupancy prediction, HVAC model predictive control (MPC) validation, and fault detection diagnostics[citation:7].
- Data Quality: Underwent a rigorous three-step curation process: data cleaning, metadata modeling using the Brick schema, and representation via a semantic JSON schema for high quality and usability[citation:7].
📊 View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Kaggle.
Preview on Kaggle
Cite This Dataset
Luo, N., Wang, Z., Blum, D., Weyandt, C., Granderson, J., Spanos, C. J., & Hong, T. (2022). A three-year dataset supporting research on building energy management and occupancy analytics. {Scientific Data. [Dataset]. {Nature Portfolio. https://doi.org/10.1038/s41597-022-01257-x
Select your preferred citation style above. The citation will automatically update and you can copy it to your clipboard.
Original source: {Nature Portfolio (2022). Visit official page for more details.
Indexed by IoTDataset.com on Feb 10, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.