FLANdERS
| project staff | description | Data records | publications
|
Chair of computer architecture | |
Benjamin Voelker, M.Sc. | developer |
FLANdERS - a Fully Labeled AppliaNce ElectRicity dataSet
FLANdERS contains power consumption profiles of several electrical household appliances. The aim of this dataset is to advance research in the area of electricity analytics and load monitoring.
FLANdERS contains power consumption profiles of several electrical household appliances. The aim of this dataset is to advance research in the area of electricity analytics and load monitoring.
We recorded data of category 2-4 devices according to G.W. Hart [1] (Cat1: Permanent On; Cat2: On-Off; Cat3: Finite State Machines; Cat4: Consumer Variable Device). The profiles have been labeled manually to show all (internal) states and state changes of the monitored appliance.
The profiles were recorded using custom build plugs which record voltage, current as well as active- and reactive power. We chose a sampling rate of 4kHz to be able to analyze frequencies up to 2kHz. All data is stored as a wavpack encoded audio stream inside a matroska multimedia container (MKV). The ground truth data is encoded as a subtitle in ASS format and embedded as a second stream inside the MKV. To load the data, you can use e.g. the open source toolkit FFmpeg.
This database is made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/.
Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/
If you use the FLANdERS database for your scientific publications, please cite the following:
Benjamin Völker, Philipp M. Scholl, Bernd Becker: Semi-Automatic Generation and Labeling of Training Data for Non-Intrusive Load Monitoring. Proceedings of the Tenth ACM International Conference on Future Energy Systems (ACM e-Energy), 2019.
If you use the FLANdERS database for your scientific publications, please cite the following:
Benjamin Völker, Philipp M. Scholl, Bernd Becker: Semi-Automatic Generation and Labeling of Training Data for Non-Intrusive Load Monitoring. Proceedings of the Tenth ACM International Conference on Future Energy Systems (ACM e-Energy), 2019.
For more information, or if you want to contribute to the dataset, have a look at the git repository: https://projects.informatik.uni-freiburg.de/projects/smartenergy/wiki/Datasets.
Files are organized in the following way.
Filename:
"devicetype__brand__modelNumber__powerRating__year_mon_date__hour_min_sec.mkv"
Filetype:
Matroska Multimedia Container with two streams:
Stream 0: Wavpack encoded audio stream
Stream 1: Ass encoded subtitle stream
Link:
Download
Filename:
"devicetype__brand__modelNumber__powerRating__year_mon_date__hour_min_sec.mkv"
Filetype:
Matroska Multimedia Container with two streams:
Stream 0: Wavpack encoded audio stream
Stream 1: Ass encoded subtitle stream
Link:
Download
Benjamin Voelker, M.Sc. |