Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks
Appliance recognition is one of the vital sub-tasks of NILM in which a machine learning classier is used to detect and recognize active appliances from power measurements. The performance of the appliance classifier highly depends on the signal features used to characterize the loads. Recently, diff...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/13/3374 |
| _version_ | 1797563580777758720 |
|---|---|
| author | Anthony Faustine Lucas Pereira |
| author_facet | Anthony Faustine Lucas Pereira |
| author_sort | Anthony Faustine |
| collection | DOAJ |
| description | Appliance recognition is one of the vital sub-tasks of NILM in which a machine learning classier is used to detect and recognize active appliances from power measurements. The performance of the appliance classifier highly depends on the signal features used to characterize the loads. Recently, different appliance features derived from the voltage–current (V–I) waveforms have been extensively used to describe appliances. However, the performance of V–I-based approaches is still unsatisfactory as it is still not distinctive enough to recognize devices that fall into the same category. Instead, we propose an appliance recognition method utilizing the recurrence graph (RG) technique and convolutional neural networks (CNNs). We introduce the weighted recurrent graph (WRG) generation that, given one-cycle current and voltage, produces an image-like representation with more values than the binary output created by RG. Experimental results on three different sub-metered datasets show that the proposed WRG-based image representation provides superior feature representation and, therefore, improves classification performance compared to V–I-based features. |
| first_indexed | 2024-03-10T18:44:36Z |
| format | Article |
| id | doaj.art-81ec882f82cb45328634e8290b2192b1 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T18:44:36Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-81ec882f82cb45328634e8290b2192b12023-11-20T05:33:57ZengMDPI AGEnergies1996-10732020-07-011313337410.3390/en13133374Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural NetworksAnthony Faustine0Lucas Pereira1Ireland’s National Centre for Applied Data Analytics (CeADER), University College Dublin, Dublin 4, IrelandITI, LARSyS, Técnico Lisboa, 1049-001 Lisboa, PortugalAppliance recognition is one of the vital sub-tasks of NILM in which a machine learning classier is used to detect and recognize active appliances from power measurements. The performance of the appliance classifier highly depends on the signal features used to characterize the loads. Recently, different appliance features derived from the voltage–current (V–I) waveforms have been extensively used to describe appliances. However, the performance of V–I-based approaches is still unsatisfactory as it is still not distinctive enough to recognize devices that fall into the same category. Instead, we propose an appliance recognition method utilizing the recurrence graph (RG) technique and convolutional neural networks (CNNs). We introduce the weighted recurrent graph (WRG) generation that, given one-cycle current and voltage, produces an image-like representation with more values than the binary output created by RG. Experimental results on three different sub-metered datasets show that the proposed WRG-based image representation provides superior feature representation and, therefore, improves classification performance compared to V–I-based features.https://www.mdpi.com/1996-1073/13/13/3374non-intrusive load monitoringappliance classificationappliance featurerecurrence graphweighted recurrence graphV–I trajectory |
| spellingShingle | Anthony Faustine Lucas Pereira Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks Energies non-intrusive load monitoring appliance classification appliance feature recurrence graph weighted recurrence graph V–I trajectory |
| title | Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks |
| title_full | Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks |
| title_fullStr | Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks |
| title_full_unstemmed | Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks |
| title_short | Improved Appliance Classification in Non-Intrusive Load Monitoring Using Weighted Recurrence Graph and Convolutional Neural Networks |
| title_sort | improved appliance classification in non intrusive load monitoring using weighted recurrence graph and convolutional neural networks |
| topic | non-intrusive load monitoring appliance classification appliance feature recurrence graph weighted recurrence graph V–I trajectory |
| url | https://www.mdpi.com/1996-1073/13/13/3374 |
| work_keys_str_mv | AT anthonyfaustine improvedapplianceclassificationinnonintrusiveloadmonitoringusingweightedrecurrencegraphandconvolutionalneuralnetworks AT lucaspereira improvedapplianceclassificationinnonintrusiveloadmonitoringusingweightedrecurrencegraphandconvolutionalneuralnetworks |