Non-Intrusive Load Disaggregation by Convolutional Neural Network and Multilabel Classification
Source abstract
Abstract
Non-intrusive load monitoring (NILM) is the main method used to monitor the energy footprint of a residential building and disaggregate total electrical usage into appliance-related signals. The most common disaggregation algorithms are based on the Hidden Markov Model, while solutions based on deep neural networks have recently caught the attention of researchers. In this work we address the problem through the recognition of the state of activation of the appliances using a fully convolutional deep neural network, borrowing some techniques used in the semantic segmentation of images and multilabel classification. This approach has allowed obtaining high performances not only in the recognition of the activation state of the domestic appliances but also in the estimation of their consumptions, improving the state of the art for a reference dataset.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Grid Energy Management · Building Energy and Comfort Optimization · Energy Load and Power Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
CRS4, Center for Advanced Studies, Research and Development in Sardinia, loc. Piscina Manna ed. 1, 09050 Pula (CA), Italy
Funding
Regione Autonoma della Sardegna
References (55)
Show source-provided references
1. Nonintrusive load monitoring algorithm using mixed-integer linear programming10.1109/TCE.2018.2843292 ↗
2. Is disaggregation the holy grail of energy efficiency? The case of electricity10.1016/j.enpol.2012.08.062 ↗
3. A smart home energy management system using IoT and big data analytics approach10.1109/TCE.2017.015014 ↗
4. Smart home energy management system using IEEE 802.15. 4 and zigbee10.1109/TCE.2010.5606276 ↗
5. A review disaggregation method in Non-intrusive Appliance Load Monitoring10.1016/j.rser.2016.07.009 ↗
6. Non-intrusive load monitoring through home energy management systems: A comprehensive review10.1016/j.rser.2017.05.096 ↗
7. Review of smart meter data analytics: Applications, methodologies, and challenges10.1109/TSG.2018.2818167 ↗
8. Ruano, A., Hernandez, A., Ureña, J., Ruano, M., and Garcia, J. (2019). NILM techniques for intelligent home energy management and ambient assisted living: A review. Energies, 12.10.3390/en12112203 ↗
9. Analysis of trends in seasonal electrical energy consumption via non-negative tensor factorization10.1016/j.neucom.2015.03.088 ↗
10. Makonin, S.W. (2014). Real-Time Embedded Low-Frequency Load Disaggregation. [Ph.D. Thesis, Applied Sciences: School of Computing Science, Simon Fraser University].
11. Electric load signature analysis for home energy monitoring system10.5391/IJFIS.2012.12.3.193 ↗
12. Elhamifar, E., and Sastry, S. (2015). Energy Disaggregation via Learning Powerlets and Sparse Coding, AAAI.10.1609/aaai.v29i1.9249 ↗
13. Hasan, M., Chowdhury, D., Khan, M., and Rahman, Z. (2019). Non-Intrusive Load Monitoring Using Current Shapelets. Appl. Sci., 9.10.3390/app9245363 ↗
14. Feature extraction for load identification using long-term operating waveforms10.1109/TSG.2014.2373314 ↗
15. An efficient, scalable time-frequency method for tracking energy usage of domestic appliances using a two-step classification algorithm10.3390/en7117041 ↗
16. Power-spectrum-based wavelet transform for nonintrusive demand monitoring and load identification10.1109/TIA.2013.2283318 ↗
17. Development of an improved time–frequency analysis-based nonintrusive load monitor for load demand identification10.1109/TIM.2013.2289700 ↗
18. An empirical investigation of VI trajectory based load signatures for non-intrusive load monitoring10.1109/TSG.2013.2271282 ↗
19. Non-intrusive load monitoring algorithm based on features of V–I trajectory10.1016/j.epsr.2017.12.012 ↗
20. Bouhouras, A.S., Gkaidatzis, P.A., Chatzisavvas, K.C., Panagiotou, E., Poulakis, N., and Christoforidis, G.C. (2017). Load signature formulation for non-intrusive load monitoring based on current measurements. Energies, 10.10.3390/en10040538 ↗
21. A NILM algorithm with enhanced disaggregation scheme under harmonic current vectors10.1016/j.enbuild.2018.11.013 ↗
22. Sparse optimization for automated energy end use disaggregation10.1109/TCST.2015.2476777 ↗
23. Wang, H., and Yang, W. (2018). An iterative load disaggregation approach based on appliance consumption pattern. Appl. Sci., 8.10.3390/app8040542 ↗
24. Wytock, M., and Kolter, J.Z. (2014, January 27–31). Contextually supervised source separation with application to energy disaggregation. Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, Québec City, QC, Canada.10.1609/aaai.v28i1.8769 ↗
25. Improving nonintrusive load monitoring efficiency via a hybrid programing method10.1109/TII.2016.2590359 ↗
26. An extensible approach for non-intrusive load disaggregation with smart meter data10.1109/TSG.2016.2631238 ↗
27. Egarter, D., Sobe, A., and Elmenreich, W. (2013, January 3–5). Evolving non-intrusive load monitoring. Proceedings of the European Conference on the Applications of Evolutionary Computation, Vienna, Austria.10.1007/978-3-642-37192-9_19 ↗
28. Lucas, A., Jansen, L., Andreadou, N., Kotsakis, E., and Masera, M. (2019). Load Flexibility Forecast for DR Using Non-Intrusive Load Monitoring in the Residential Sector. Energies, 12.10.3390/en12142725 ↗
29. Non-intrusive demand monitoring and load identification for energy management systems based on transient feature analyses10.3390/en5114569 ↗
30. Kelly, J., and Knottenbelt, W. (2015, January 4–8). Neural NILM: Deep neural networks applied to energy disaggregation. Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, Bengaluru, India.10.1145/2821650.2821672 ↗
31. Zhang, C., Zhong, M., Wang, Z., Goddard, N., and Sutton, C. (2018, January 2–7). Sequence-to-point learning with neural networks for non-intrusive load monitoring. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11873 ↗
32. Denoising autoencoders for non-intrusive load monitoring: Improvements and comparative evaluation10.1016/j.enbuild.2017.11.054 ↗
33. Barsim, K.S., and Yang, B. (2018). On the feasibility of generic deep disaggregation for single-load extraction. arXiv.
34. Fagiani, M., Bonfigli, R., Principi, E., Squartini, S., and Mandolini, L. (2019). A Non-Intrusive Load Monitoring Algorithm Based on Non-Uniform Sampling of Power Data and Deep Neural Networks. Energies, 12.10.3390/en12071371 ↗
35. Non-intrusive load disaggregation based on deep dilated residual network10.1016/j.epsr.2019.01.034 ↗
36. Wu, Q., and Wang, F. (2019). Concatenate convolutional neural networks for non-intrusive load monitoring across complex background. Energies, 12.10.3390/en12081572 ↗
37. Mauch, L., and Yang, B. (2015, January 14–16). A new approach for supervised power disaggregation by using a deep recurrent LSTM network. Proceedings of the 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Orlando, FL, USA.10.1109/GlobalSIP.2015.7418157 ↗
38. Rafiq, H., Zhang, H., Li, H., and Ochani, M.K. (2018, January 12–15). Regularized LSTM Based Deep Learning Model: First Step towards Real-Time Non-Intrusive Load Monitoring. Proceedings of the 2018 IEEE International Conference on Smart Energy Grid Engineering (SEGE), Oshawa, ON, Canada.10.1109/SEGE.2018.8499519 ↗
39. Kim, J.G., and Lee, B. (2019). Appliance classification by power signal analysis based on multi-feature combination multi-layer LSTM. Energies, 12.10.3390/en12142804 ↗
40. Salerno, V.M., and Rabbeni, G. (2018). An extreme learning machine approach to effective energy disaggregation. Electronics, 7.10.20944/preprints201808.0551.v1 ↗
41. Kramer, O., Wilken, O., Beenken, P., Hein, A., Hüwel, A., Klingenberg, T., Meinecke, C., Raabe, T., and Sonnenschein, M. (2012, January 4–7). On ensemble classifiers for nonintrusive appliance load monitoring. Proceedings of the International Conference on Hybrid Artificial Intelligence Systems, Hong Kong, China.10.1007/978-3-642-28942-2_29 ↗
42. Figueiredo, M.B., De Almeida, A., and Ribeiro, B. (2011, January 14–16). An experimental study on electrical signature identification of non-intrusive load monitoring (nilm) systems. Proceedings of the International Conference on Adaptive and Natural Computing Algorithms, Ljubljana, Slovenia.10.1007/978-3-642-20267-4_4 ↗
43. Wu, X., Gao, Y., and Jiao, D. (2019). Multi-label classification based on random forest algorithm for non-intrusive load monitoring system. Processes, 7.10.3390/pr7060337 ↗
44. He, H., Liu, Z., Jiao, R., and Yan, G. (2019). A novel nonintrusive load monitoring approach based on linear-chain conditional random fields. Energies, 12.10.3390/en12091797 ↗
45. Real-time recognition non-intrusive electrical appliance monitoring algorithm for a residential building energy management system10.3390/en8099029 ↗
46. A hybrid signature-based iterative disaggregation algorithm for non-intrusive load monitoring10.1016/j.apenergy.2016.10.040 ↗
47. Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring10.1109/TSG.2015.2494592 ↗
48. A cloud-based on-line disaggregation algorithm for home appliance loads10.1109/TSG.2018.2826844 ↗
49. Desai, S., Alhadad, R., Mahmood, A., Chilamkurti, N., and Rho, S. (2019). Multi-State Energy Classifier to Evaluate the Performance of the NILM Algorithm. Sensors, 19.10.3390/s19235236 ↗
50. Yu, J., Gao, Y., Wu, Y., Jiao, D., Su, C., and Wu, X. (2019). Non-Intrusive Load Disaggregation by Linear Classifier Group Considering Multi-Feature Integration. Appl. Sci., 9.10.20944/preprints201906.0169.v1 ↗
51. Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21–26). Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.660 ↗
52. Cui, Y., Jia, M., Lin, T.Y., Song, Y., and Belongie, S. (2019, January 16–20). Class-Balanced Loss Based on Effective Number of Samples. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00949 ↗
53. Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017, January 8). Automatic Differentiation in PyTorch. Proceedings of the NIPS Autodiff Workshop, Long Beach, CA, USA.
54. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes10.1038/sdata.2015.7 ↗
55. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.