Non-Intrusive Load Monitoring of Buildings Using Spectral Clustering
With widely deployed smart meters, non-intrusive energy measurements have become feasible, which may benefit people by furnishing a better understanding of appliance-level energy consumption. This work is a step forward in using graph signal processing for non-intrusive load monitoring (NILM) by pro...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/11/4036 |
| _version_ | 1797491760257040384 |
|---|---|
| author | Muzzamil Ghaffar Shakil R. Sheikh Noman Naseer Zia Mohy Ud Din Hafiz Zia Ur Rehman Muhammad Naved |
| author_facet | Muzzamil Ghaffar Shakil R. Sheikh Noman Naseer Zia Mohy Ud Din Hafiz Zia Ur Rehman Muhammad Naved |
| author_sort | Muzzamil Ghaffar |
| collection | DOAJ |
| description | With widely deployed smart meters, non-intrusive energy measurements have become feasible, which may benefit people by furnishing a better understanding of appliance-level energy consumption. This work is a step forward in using graph signal processing for non-intrusive load monitoring (NILM) by proposing two novel techniques: the spectral cluster mean (SC-M) and spectral cluster eigenvector (SC-EV) methods. These methods use spectral clustering for extracting individual appliance energy usage from the aggregate energy profile of the building. After clustering the data, different strategies are employed to identify each cluster and thus the state of each device. The SC-M method identifies the cluster by comparing its mean with the devices’ pre-defined profiles. The SC-EV method employs an eigenvector resultant to locate the event and then recognize the device using its profile. An ideal dataset and a real-world REFIT dataset are used to test the performance of these two techniques. The f-measure score and disaggregation accuracy of the proposed techniques demonstrate that these two techniques are competitive and viable, with advantages of low complexity, high accuracy, no training data requirement, and fast processing time. Therefore, the proposed techniques are suitable candidates for NILM. |
| first_indexed | 2024-03-10T00:53:52Z |
| format | Article |
| id | doaj.art-773f16214a464401a0f8cc53e3ddbfbc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:53:52Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-773f16214a464401a0f8cc53e3ddbfbc2023-11-23T14:47:39ZengMDPI AGSensors1424-82202022-05-012211403610.3390/s22114036Non-Intrusive Load Monitoring of Buildings Using Spectral ClusteringMuzzamil Ghaffar0Shakil R. Sheikh1Noman Naseer2Zia Mohy Ud Din3Hafiz Zia Ur Rehman4Muhammad Naved5Department of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad 44000, PakistanWith widely deployed smart meters, non-intrusive energy measurements have become feasible, which may benefit people by furnishing a better understanding of appliance-level energy consumption. This work is a step forward in using graph signal processing for non-intrusive load monitoring (NILM) by proposing two novel techniques: the spectral cluster mean (SC-M) and spectral cluster eigenvector (SC-EV) methods. These methods use spectral clustering for extracting individual appliance energy usage from the aggregate energy profile of the building. After clustering the data, different strategies are employed to identify each cluster and thus the state of each device. The SC-M method identifies the cluster by comparing its mean with the devices’ pre-defined profiles. The SC-EV method employs an eigenvector resultant to locate the event and then recognize the device using its profile. An ideal dataset and a real-world REFIT dataset are used to test the performance of these two techniques. The f-measure score and disaggregation accuracy of the proposed techniques demonstrate that these two techniques are competitive and viable, with advantages of low complexity, high accuracy, no training data requirement, and fast processing time. Therefore, the proposed techniques are suitable candidates for NILM.https://www.mdpi.com/1424-8220/22/11/4036non-intrusive load monitoringenergy disaggregationspectral clusteringgraph signal processingdemand-side energy managementsmart buildings |
| spellingShingle | Muzzamil Ghaffar Shakil R. Sheikh Noman Naseer Zia Mohy Ud Din Hafiz Zia Ur Rehman Muhammad Naved Non-Intrusive Load Monitoring of Buildings Using Spectral Clustering Sensors non-intrusive load monitoring energy disaggregation spectral clustering graph signal processing demand-side energy management smart buildings |
| title | Non-Intrusive Load Monitoring of Buildings Using Spectral Clustering |
| title_full | Non-Intrusive Load Monitoring of Buildings Using Spectral Clustering |
| title_fullStr | Non-Intrusive Load Monitoring of Buildings Using Spectral Clustering |
| title_full_unstemmed | Non-Intrusive Load Monitoring of Buildings Using Spectral Clustering |
| title_short | Non-Intrusive Load Monitoring of Buildings Using Spectral Clustering |
| title_sort | non intrusive load monitoring of buildings using spectral clustering |
| topic | non-intrusive load monitoring energy disaggregation spectral clustering graph signal processing demand-side energy management smart buildings |
| url | https://www.mdpi.com/1424-8220/22/11/4036 |
| work_keys_str_mv | AT muzzamilghaffar nonintrusiveloadmonitoringofbuildingsusingspectralclustering AT shakilrsheikh nonintrusiveloadmonitoringofbuildingsusingspectralclustering AT nomannaseer nonintrusiveloadmonitoringofbuildingsusingspectralclustering AT ziamohyuddin nonintrusiveloadmonitoringofbuildingsusingspectralclustering AT hafizziaurrehman nonintrusiveloadmonitoringofbuildingsusingspectralclustering AT muhammadnaved nonintrusiveloadmonitoringofbuildingsusingspectralclustering |