Datasets
Our data can be your basis
Explore our datasets covering multiple scales of the built environment, from urban energy use and building portfolios to individual rooms and technical systems. We publish data to support transparency, reproducibility, and further research.
Datasets
Datasets
License
Creative Commons Attribution 4.0 International
Description
The dataset comprises Building Management System (BMS) data from an educational building located on the main campus of Aalborg University in Denmark, as well as from Empa’s NEST (Next Evolution in Sustainable Building Technologies) demonstrator building in Switzerland. The buildings contain main and sub-meters for all equipment using electricity or thermal energy. The equipment using thermal energy includes air handling units (water-based heating coils), space heating (floor heating, radiators, and ceiling heating), and domestic hot water (heat exchangers). Besides the energy data, room data, such as temperature, CO2 concentration, occupant presence, radiator valve opening, and ventilation damper opening, are included for all rooms in the buildings. The data spans 6 to 28 months, depending on the building and the measurement points. The data was collected as raw data with a time resolution between 1 and 10 min. The dataset is expected to be useful for various applications, including model calibration, machine learning, and occupant analysis.
Read more here
License
Creative Commons Attribution 4.0 International
Description
The dataset includes one year of manually labelled daily occupancy and hourly water use for ten Danish single-family houses, labelled by five independent annotators. It also contains diary-based hourly occupancy and water use for eight residential buildings over 122 days. Electricity use is available for seven buildings, while appliance-use information during unoccupied periods is available for six. Processing and data-collection code is included.
Read more here
License
Creative Commons Attribution 4.0 International
Description
The operational building data presented in this paper has been collected from six office rooms located in an office building (research and educational purposes) located on the main campus of Aalborg University in Denmark. The dataset consists of measurements of occupancy, indoor environmental quality, room-level and system-level heating, ventilation and lighting operation at a 5 min resolution. The indoor environmental quality and building system data were collected from the building management system. The occupancy level in each monitored room is established from the computer vision-based analysis of wall-mounted camera footage of each office. The number of people present in the room is estimated using the YOLOv5s image recognition algorithm. The present dataset can be used for occupancy analysis, indoor environmental quality investigations, machine learning, and model predictive control.
Read more here
License
Creative Commons Attribution 4.0 International
Description
A CSV dataset containing room-level indoor environmental quality measurements and occupancy ground truth from five Danish residential apartments. The data cover seven days in January and February 2023 at a 15-minute resolution. Indoor CO₂ concentration, operative temperature, and relative humidity are included alongside engineered features describing short-term environmental dynamics. Metadata cover apartment, room, room type, floor area, date, and time. Occupancy is represented as a binary room-level variable based on resident activity logbooks.
Read more here
License
Restricted
Description
This dataset includes data from 34,884 commercial smart heat meters and 10,765 commercial smart water meters, covering a period of up to 5 years (2018 - 2022). The data originates from single-family houses in Aalborg Municipality, Denmark. Additionally, comprehensive building characteristics were collected for each building, where available, from the Danish Building and Dwelling Register (BBR) and Energy Performance Certificate (EPC) input data. As a result, up to 86 distinct characteristics per building are available. A well-established methodology was applied to process all smart meter data, resulting in equidistant hourly data with no erroneous or missing values. Rule sets were further employed to filter the building characteristics derived from the EPCs, enhancing the data quality.
Read more here
License
Creative Commons Attribution 4.0 International
Description
This dataset includes three years of cleaned hourly data from 3021 commercial smart heat meters installed in Danish residential buildings. The data are screened, interpolated to be equidistant, and missing values were imputed using a weighted moving average combined with a scaling algorithm to obey the data's cumulative trend. The original (anonymised) raw data of 3127 smart heat meters are also provided to increase transparency and reproducibility. Together with the consumption data, contextual information about the construction year, the type of building, and, if available, the energy label for the smart heat meters buildings (for all 3127 buildings of the raw data) are provided. The unique meter ID can link this data to the consumption data. A .pdf document describing the purpose of every data column is given in the folder '01_Data'. Besides this, three figures visualising the z-normalised data in different temporal resolutions are provided. Next to the data and the data visualisation, all code, written in R, used for data processing and extensive technical validation of the data is included.
Read more here