This dataset was curated from an office building constructed in 2015 in Berkeley, California, which includes whole-building and end-use energy consumption, HVAC system operating conditions, indoor and outdoor environmental parameters, and occupant counts. The data was collected in three years from more than 300 sensors and meters for two office floors (each 2,325 m2) of the building. A three-step data curation strategy is applied to transform the raw data into the research-grade data: (1) cleaning the raw data to detect and adjust the outlier values and fill the data gaps; (2) creating the metadata model of the building systems and data points using the Brick schema; (3) describing the metadata of the dataset using a semantic JSON schema. This dataset can be used for various types of applications, including building energy benchmarking, load shape analysis, energy prediction, occupancy prediction and analytics, and HVAC controls to improve understanding and efficiency of building operations for reducing energy use, energy costs, and carbon emissions.

This dataset includes data of whole-building and end-use energy consumption, HVAC system operating conditions, indoor and outdoor environmental parameters, and occupant counts. The data was collected in three years from more than 300 sensors and meters for two office floors of the building. A three-step data curation strategy is applied to transform the raw data into the research-grade data: (1) cleaning the raw data to detect and adjust the outlier values and fill the data gaps; (2) creating the metadata model of the building systems and data points using the Brick schema; (3) describing the metadata of the dataset using a semantic JSON schema.

The time-series data is in CSV format and has a size of 2.38 GB. A more detailed note about the data cleaning strategy is available at the dataset’s GitHub page - https://github.com/LBNL-ETA/Data-Cleaning. We recommend users to explore the metadata of equipment and sensors in the Brick model by using the Brick TTL viewer. Users can obtain the high-level metadata about the building and dataset in the metadata JSON file.