An unsupervised training method for non-intrusive appliance load monitoring
- Submitting institution
-
University of Oxford
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2014
- Type
- D - Journal article
- DOI
-
10.1016/j.artint.2014.07.010
- Title of journal
- Artificial Intelligence
- Article number
- -
- First page
- 1
- Volume
- 217
- Issue
- -
- ISSN
- 0004-3702
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 88
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes a novel algorithm to provide households with appliance level electricity consumption data from a single aggregate meter read at 10 second intervals. Unlike prior approaches, this one is unsupervised, and does not require sub-metering data, or manually generated labels. This work led directly to the release of the open-source non-intrusive load monitoring toolkit (NILMTK) for comparing NILM approaches, which currently has 18 active maintainers and has been forked over 200 times, and the founding of the European NILM Workshop in 2014, which each year bring together academics and industrial researchers working on non-intrusive load monitoring.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -