May 2016 release of the
UK Domestic Appliance-Level Electricity (UK-DALE) dataset

This dataset records the power demand from five houses. In each house we record both the whole-house mains power demand every six seconds as well as power demand from individual appliances every six seconds. In three of the six houses we also record the whole-house voltage and current at 16 kHz and every second.

This dataset will be updated as more data is recorded. Each release of the dataset is labelled with the month and year. The most recent release is for May 2016. UK-DALE now includes 3.5 years of data for house 1.


The following paper describes the data recording system and the January 2015 release of the dataset. Please cite this paper if you use the dataset or the recording hardware:

Jack Kelly and William Knottenbelt. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific Data 2, Article number:150007, 2015, DOI:10.1038/sdata.2015.7


  Title        = {The {UK-DALE} dataset, domestic appliance-level
                  electricity demand and whole-house demand from five {UK} homes},
  Author       = {Jack Kelly and William Knottenbelt},
  Journaltitle = {Scientific Data},
  Year         = {2015},
  Date         = {2015/03/31},
  Number       = {150007},
  Volume       = {2},
  Doi          = {10.1038/sdata.2015.7}


  title        = {The {UK-DALE} dataset, domestic appliance-level
                  electricity demand and whole-house demand from five {UK} homes},
  author       = {Jack Kelly and William Knottenbelt},
  journal      = {Scientific Data},
  year         = {2015},
  date         = {2015/03/31},
  number       = {150007},
  volume       = {2},
  doi          = {10.1038/sdata.2015.7}

Small correction to the paper

The paper states:

The uncompressed 16 kHz 24-bit files would require 28.8 GBytes per day so we compress the files using the Free Lossless Audio Codec (FLAC) to reduce the storage requirements to ≈ 4.8 GBytes per day.

In fact, the uncompressed 16 kHz 24-bit files require 8.3 GBytes per day, not 28.8 GBytes per day!


1-second and 6-second data

The January 2015 release of the 1 second and 6 second data are available from the UK Energy Research Council's Energy Data Centre using our dataset DOI:10.5286/UKERC.EDC.000001 (please cite this DOI if you use the dataset). The UKERC EDC also provide a nice web interface to explore the files.

Alternatively, you can download the May 2016 data from Imperial where the 1-second and 6-second data is provided in three formats: CSV files in a .zip archive (intended primarily for Windows users); CSV files in a .tgz archive (intended primarily for Linux and Mac OS users); and a .H5 file (using the NILMTK file format).

zip version

Download the .zip archive.

tgz version

A tgz file is a tarball: a collection of files in a tar archive, which is then compressed using gzip. It is equivalent to tar.gz

Download the gzipped tarball.

Extract the file using:

tar xvzf uk-power-data-download.tgz

H5 version

The May 2016 H5 version of the 1-second and 6-second data (for use with NILMTK) can be downloaded via FTP from Imperial. For the FTP server details, please see the section below called "The full 16 kHz dataset via FTP".

Alternatively, the January 2015 version of the H5 file can be downloaded from the UKERC EDC.

Utility meters

Gas and electricity utility meter readings for house 1 are available in two formats:

16kHz data

The complete May 2016 version of the 16kHz dataset occupies 6 TBytes. The full Jan 2015 release of the dataset can be downloaded from the UKERC EDC via dataset DOI:10.5286/UKERC.EDC.000002 (please cite this DOI if you use this dataset) or, alternatively, the May 2016 dataset can be downloaded using FTP (see below) from Imperial. We also have two subsets of the data available for download:

Inside each tar file is a set of 1-hour flac files. The name of each flac file is the UNIX timestamp at the start of the recording for that flac file. The underscore in the filename should be interpreted as a decimal mark (i.e. it separates the integer part from the fractional part of the UNIX timstamp).

For more info about the high frequency data, please see our paper and the snd_card_power_meter github repository (the code we used to record the high frequency data.)

Converting from FLAC files to volts and amps

First you probably want to convert from FLAC (a lossless audio compression) to WAV. There are many audio tools that can convert from FLAC to WAV. I often use sox.

Once you have the WAV file, you'll need to convert from the [-1,1] range of values in the WAV file to volts and amps. You'll need the calibration.cfg file for the house in question. This file specifies an amps_per_adc_step parameter and a volts_per_adc_step parameter. To calculate volts from the WAV files, use this formula: volts_per_adc_step × number_of_ADC_steps × value_from_wav_file. The variable number_of_ADC_steps=231 for houses 1 and 2 and number_of_ADC_steps=215 for house 5. Use a similar formula for amps. (The software we use for recording the data used 32-bit integers to capture the audio signal for houses 1 and 2 and 16-bit integers for house 5. Hence, for houses 1 and 2, there are 232 ADC steps for the full range from [-1,1] and 231 ADC steps for half the range from [0,1] or [-1,0].) You can safely ignore the 'phase_difference' parameter and just assume that the measurement hardware introduces no significant phase shift.

The full 16 kHz dataset via FTP

The full 16 kHz data set is available for download via FTP. The data are stored as a sequence of FLAC files. Each FLAC file is about 200 MBytes. This FTP server is actually my own office PC. Please email me at jack dot kelly at imperial dot ac dot uk if you have any problems connecting.

I'd recommend using a 'proper' FTP client program to connect (because it will give useful error messages and be able to resume downloading if the network connection fails). For example, you could use FileZilla (it's free and open-source). Or, if you're feeling lazy, you could try just pointing your web browser to

You should be able to establish an anonymous FTP connection using these details (please note the unusual port!):

      port: 55555
  username: anonymous
  password: <your email address>

Then navigate to the 'flac' directory and download any files you want ;).

File format details

The paper listed above provides a good introduction to the dataset. Exact details are included in the README. The data format is described here. The metadata supplied with UK-DALE follows the NILM Metadata schema.

Change log

May 2016 release

August 2015 release

January 2015 release


Contact Jack Kelly, the guy who maintains this dataset.