Energy Disaggregation Using Two-Stage Fusion of Binary Device Detectors
A data-driven methodology to improve the energy disaggregation accuracy during Non-Intrusive Load Monitoring is proposed. In detail, the method uses a two-stage classification scheme, with the first stage consisting of classification models processing the aggregated signal in parallel and each of th...
| Päätekijät: | , , |
|---|---|
| Aineistotyyppi: | Artikkeli |
| Kieli: | English |
| Julkaistu: |
MDPI AG
2020-05-01
|
| Sarja: | Energies |
| Aiheet: | |
| Linkit: | https://www.mdpi.com/1996-1073/13/9/2148 |
| _version_ | 1827717694140448768 |
|---|---|
| author | Pascal A. Schirmer Iosif Mporas Akbar Sheikh-Akbari |
| author_facet | Pascal A. Schirmer Iosif Mporas Akbar Sheikh-Akbari |
| author_sort | Pascal A. Schirmer |
| collection | DOAJ |
| description | A data-driven methodology to improve the energy disaggregation accuracy during Non-Intrusive Load Monitoring is proposed. In detail, the method uses a two-stage classification scheme, with the first stage consisting of classification models processing the aggregated signal in parallel and each of them producing a binary device detection score, and the second stage consisting of fusion regression models for estimating the power consumption for each of the electrical appliances. The accuracy of the proposed approach was tested on three datasets—ECO (Electricity Consumption & Occupancy), REDD (Reference Energy Disaggregation Data Set), and iAWE (Indian Dataset for Ambient Water and Energy)—which are available online, using four different classifiers. The presented approach improves the estimation accuracy by up to 4.1% with respect to a basic energy disaggregation architecture, while the improvement on device level was up to 10.1%. Analysis on device level showed significant improvement of power consumption estimation accuracy especially for continuous and nonlinear appliances across all evaluated datasets. |
| first_indexed | 2024-03-10T20:07:01Z |
| format | Article |
| id | doaj.art-f5d070ec80b4442687807b901b97dc0d |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T20:07:01Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-f5d070ec80b4442687807b901b97dc0d2023-11-19T23:12:21ZengMDPI AGEnergies1996-10732020-05-01139214810.3390/en13092148Energy Disaggregation Using Two-Stage Fusion of Binary Device DetectorsPascal A. Schirmer0Iosif Mporas1Akbar Sheikh-Akbari2Communications and Intelligent Systems Group, School of Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UKCommunications and Intelligent Systems Group, School of Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UKSchool of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds LS1 3HE, UKA data-driven methodology to improve the energy disaggregation accuracy during Non-Intrusive Load Monitoring is proposed. In detail, the method uses a two-stage classification scheme, with the first stage consisting of classification models processing the aggregated signal in parallel and each of them producing a binary device detection score, and the second stage consisting of fusion regression models for estimating the power consumption for each of the electrical appliances. The accuracy of the proposed approach was tested on three datasets—ECO (Electricity Consumption & Occupancy), REDD (Reference Energy Disaggregation Data Set), and iAWE (Indian Dataset for Ambient Water and Energy)—which are available online, using four different classifiers. The presented approach improves the estimation accuracy by up to 4.1% with respect to a basic energy disaggregation architecture, while the improvement on device level was up to 10.1%. Analysis on device level showed significant improvement of power consumption estimation accuracy especially for continuous and nonlinear appliances across all evaluated datasets.https://www.mdpi.com/1996-1073/13/9/2148energy disaggregationnon-intrusive load monitoringregression fusion |
| spellingShingle | Pascal A. Schirmer Iosif Mporas Akbar Sheikh-Akbari Energy Disaggregation Using Two-Stage Fusion of Binary Device Detectors Energies energy disaggregation non-intrusive load monitoring regression fusion |
| title | Energy Disaggregation Using Two-Stage Fusion of Binary Device Detectors |
| title_full | Energy Disaggregation Using Two-Stage Fusion of Binary Device Detectors |
| title_fullStr | Energy Disaggregation Using Two-Stage Fusion of Binary Device Detectors |
| title_full_unstemmed | Energy Disaggregation Using Two-Stage Fusion of Binary Device Detectors |
| title_short | Energy Disaggregation Using Two-Stage Fusion of Binary Device Detectors |
| title_sort | energy disaggregation using two stage fusion of binary device detectors |
| topic | energy disaggregation non-intrusive load monitoring regression fusion |
| url | https://www.mdpi.com/1996-1073/13/9/2148 |
| work_keys_str_mv | AT pascalaschirmer energydisaggregationusingtwostagefusionofbinarydevicedetectors AT iosifmporas energydisaggregationusingtwostagefusionofbinarydevicedetectors AT akbarsheikhakbari energydisaggregationusingtwostagefusionofbinarydevicedetectors |