Home Electrical Signal Disaggregation for Non-intrusive Load Monitoring (NILM) Systems



Electrical load disambiguation for end-use recognition in the smart home has become an area of study of its own right. The most notorious examples are energy monitoring, health care applications, in-home activity modeling, and home automation. Real-time energy-use analysis for whole-home approaches needs to understand where and when the electrical loads were spent. Studies have shown that individual loads can be detected (and disaggregated) from sampling the power at one single point (e.g. the electric service entrance for the house) by using a non-intrusive load monitoring (NILM) approach. In this paper, we focus on the feature extraction and pattern recognition tasks for non-intrusive residential electrical consumption traces. In par-ti-cular, we develop an algorithm capable of determining the step-changes in signals that occur whenever a device is turned on or off that allows for the definition of a unique signature (ID) for each device. For this end, features extracted from active and reactive powers and power factor are used. The classification task is carried out by support vector machines and k-nearest neighbors methods. The results illustrate the effectiveness of the proposed signature for distinguishing the different loads.


Feature Extraction and Classification, K-Nearest Neighbors, Non-Intrusive Load Monitoring, Steady-State Signatures, Support Vector Machines, Wavelet Shrinkage


Non-Intrusive Load Monitoring Systems


Neurocomputing, Elsevier, Vol. 96, pp. 66-73, Elsevier, September 2012


Cited by

Year 2018 : 3 citations

 Buddhahaia, B., Wongsereeb, W. and Rakkwamsuka, P., A non-intrusive load monitoring system using multi-label classification approach. Sustainable Cities and Society, Volume 39, Pages 621-630, 2018.

 Kwak, Y.; Hwang, J.; Lee, T. Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building. Energies 2018, 11, 1008

 Xue, Y.L., Lin, W. nd Liu, Z.Y., "Admittance-based load signature construction for non-intrusive appliance load monitoring",
Energy and Buildings, Volume 171, pp. 209-219, 2018.
DOI: 10.1016/j.enbuild.2018.04.049

Year 2017 : 9 citations

 N. Henao, K. Agbossou, S. Kelouwani, Y. Dubé and M. Fournier, "Approach in Nonintrusive Type I Load Monitoring Using Subtractive Clustering," in IEEE Transactions on Smart Grid, vol. 8, no. 2, pp. 812-821, March 2017.

 S. M. Tabatabaei, S. Dick and W. Xu, "Toward Non-Intrusive Load Monitoring via Multi-Label Classification," in IEEE Transactions on Smart Grid, vol. 8, no. 1, pp. 26-40, Jan. 2017.

 A. A. Munshi; Y. A. R. I. Mohamed, "Extracting and Defining Flexibility of Residential Electrical Vehicle Charging Loads," in IEEE Transactions on Industrial Informatics , vol.PP, no.99, pp.1-1

 Andre L.L. Aquino, Heitor S. Ramos, Alejandro C. Frery, Leonardo P. Viana, Tamer S.G. Cavalcante, Osvaldo A. Rosso, Characterization of electric load with Information Theory quantifiers, Physica A: Statistical Mechanics and its Applications, Volume 465, 2017, Pages 277-284

 D. Ponce de Leon Barido, S. Suffian, J. Rosa, E. Brewer, and D. M. Kammen. 2017. Enabling Micro-level Demand-Side Grid Flexiblity in Resource Constrained Environments. In Proceedings of the Second International Conference on Internet-of-Things Design and Implementation (IoTDI '17). ACM, New York, NY, USA, 233-245.

 Trung Kien Nguyen, Eric Dekneuvel, Gilles Jacquemod, Benjamin Nicolle, Olivier Zammit, Van Cuong Nguyen, Development of a real-time non-intrusive appliance load monitoring system: An application level model, International Journal of Electrical Power & Energy Systems, Volume 90, 2017, Pages 168-180

 Wang Sen and Yang Dongsheng and Guo Chuchen and Du Shengxian, Non-intrusive Load Disaggregation Based on Kernel Density Estimation, IOP Conference Series: Materials Science and Engineering, 199 -1, pp. 012078.

 Azaza, M., Wallin, F. "Evaluation of classification methodologies and Features selection from smart meter data ". Energy Procedia, vol 142, pp. 2250 - 2256, 2017.

 Ma, M., Lin, W., Zhang, J., Wang, P., Zhou, Y. and Liang, X. ."Toward Energy-Awareness Smart Building: Discover the Fingerprint of Your Electrical Appliances", IEEE Transactions on Industrial Informatics, Volume: 14, Issue: 4, pp: 1458 - 1468, 2018. DOI: 10.1109/TII.2017.2776300

Year 2016 : 14 citations

 Juan Diego Silva Guedes; Danton Diego Ferreira; Bruno Henrique Groenner Barbosa; Carlos Augusto Duque; Augusto Santiago Cerqueira. Non-Intrusive Appliance Load Identification Based on Higher-Order Statistics.
IEEE Latin America Transactions 10/2015; 13(10):3343-3349. DOI:10.1109/TLA.2015.7387241

 Richthammer, H., Reif, S. "Intrusion detection in the smart grid based on an analogue technique", LNCS 9591, pp. 56-67.

 Borin, V.P., Barriquello, C.H., Da Silva Martins, M.L., Campos, A., "A novel approach for home appliances identification using Vector Projection Length and Stockwell Transform ", IEEE 13th Brazilian Power Electronics Conference and 1st Southern Power Electronics Conference, COBEP/SPEC 2016 7420171

 JDS Guedes, DD Ferreira, BHG Barbosa. "A non-intrusive approach to classify electrical appliances based on higher-order statistics and genetic algorithm: a smart grid perspective", Electric Power Systems Research (Available online 15 July 2016)

 Esa, Nur Farahin, Md Pauzi Abdullah, and Mohammad Yusri Hassan. "A review disaggregation method in Non-intrusive Appliance Load Monitoring." Renewable and Sustainable Energy Reviews 66 (2016): 163-173.

 Koutitas, George C., and Leandros Tassiulas. "Low cost disaggregation of smart meter sensor data." IEEE Sensors Journal 16.6 (2016): 1665-1673.

 Shaloudegi, Kiarash, et al. "SDP Relaxation with Randomized Rounding for Energy Disaggregation." Advances in Neural Information Processing Systems. 2016.

 Kozlovskiy, Ilya; Sodenkamp, Mariya; Hopf, Konstantin; and Staake, Thorsten, "ENERGY INFORMATICS FOR
HOUSEHOLDS WITH OLD HEATING SYSTEMS" (2016). Research Papers. Paper 37. "AIS Electronic Library (AISeL)." ENERGY (2016)

 Barido, Diego Ponce de Leon, et al. "Enabling Micro-level Demand-Side Grid Flexiblity in Resource Constrained Environments." arXiv preprint arXiv:1604.08622 (2016).

 Yang, Jiajia, et al. "Mining the big data of residential appliances in the smart grid environment." Power and Energy Society General Meeting (PESGM), 2016. IEEE, 2016.

 Li, Ding, and Scott Dick. "Whole-house Non-Intrusive Appliance Load Monitoring via multi-label classification." Neural Networks (IJCNN), 2016 International Joint Conference on. IEEE, 2016.

 Ferrández-Pastor, F. J., et al. "Interpreting human activity from electrical consumption data using reconfigurable hardware and hidden Markov models." Journal of Ambient Intelligence and Humanized Computing: 1-15.

 Hoyo-Montaýo, Josý Antonio, et al. "Overview of Non-Intrusive Load Monitoring: A way to energy wise consumption." Power Electronics (CIEP), 2016 13th International Conference on. IEEE, 2016.

 I. Vassileva, J. Campillo. Consumers' Perspective on Full-Scale Adoption of Smart Meters: A Case Study in Västerås, Sweden. Resources 2016, 5(1), 3; doi:10.3390/resources5010003

Year 2015 : 8 citations

 H.Ahmadi, J.Marti. Load Decomposition at Smart Meters Level Using Eigenloads Approach. IEEE TRANSACTIONS ON POWER SYSTEMS Volume:PP , Issue: 99 (accepted for publication; DOI: 10.1109/TPWRS.2014.2388193)

 M.Singh, S. Kumar, S. Semwal,, R. S. Prasad. "Residential Load Signature Analysis for Their Segregation Using Wavelet—SVM". Power Electronics and Renewable Energy Systems, Lecture Notes in Electrical Engineering, Vol. 326, pp 863-871 (2015) (on-line since 20 Nov 2014)

 Rafsanjani, Hamed Nabizadeh; Ahn, Changbum R.; Alahmad, Mahmoud. A Review of Approaches for Sensing, Understanding, and Improving Occupancy-Related Energy-Use Behaviors in Commercial Buildings, Energies, Volume: 8 Issue: 10 Pages: 10996-11029 OCT 2015

 Makonin, Stephen; Popowich, Fred. Nonintrusive load monitoring (NILM) performance evaluation
ENERGY EFFICIENCY Volume: 8 Issue: 4 Pages: 809-814 JUL 2015

 Bonfigli, R., Squartini, S., Fagiani, M., Piazza, F. Unsupervised algorithms for non-intrusive load monitoring: An up-to-date overview Proc. 2015 IEEE 15th International Conference on Environment and Electrical Engineering, EEEIC 2015 pp. 1175-1180

 MAITRE, J.; GLON, G.; GABOURY, S.; BOUCHARD, B.; BOUZOUANE, A.. Efficient Appliances Recognition in Smart Homes Based on Active and Reactive Power, Fast Fourier Transform and Decision Trees. AAAI Workshops, North America, apr. 2015.

 S Lee, B Song, Y Kwon, J Kim. Non-intrusive Load Monitoring for Home Energy Usage with Multiple Power States Recognition. Advanced Science and Technology Letters, Vol.111 (COMCOMS 2015), pp.282-289

 Xu, Y., Milanovi?, J.V. Artificial-intelligence-based methodology for load disaggregation at bulk supply point. IEEE Transactions on Power Systems, 30(2): 795 - 803, 2015.

Year 2014 : 17 citations

 M. D. Gillman. "Interpreting human activity from electrical consumption data through non-intrusive load monitoring." PhD diss., Massachusetts Institute of Technology, USA (2014)

 Yizheng Xu, and J. V. Milanovic. "Estimation of Percentage of Controllable Load in Total Demand at Bulk Supply Point". Proc. Mediterranean Conference on Power Generation, Transmission Distribution and Energy Conversion (MEDPOWER), Greece (2014)

 Sunil Semwal, R S Prasad, Pradeep Juneja."Identifying Appliances using NIALM with Minimum Features". International Journal of Electrical and Computer Engineering (IJECE), Vol. 4, No. 6, pp. 909-922, (2014)

 N.Iksan, N.; S.H. Supangkat."Adaptive non-intrusive Load Monitoring model using Bayesian learning". Proc. , 2014 International Conference on ICT For Smart Society (ICISS), pp.232 - 235, 2014.

 Marinel Temneanu. "Appliance Characterization Based on Spectral Components Analysis". IEEE Proc. 2014 International Conference and Exposition on Electrical and Power Engineering (EPE 2014), pp. 16-18, Romania (2014)

 Xu, Yizheng, and J. V. Milanovic. "Accuracy of ANN Based Methodology for Load Composition Forecasting at Bulk Supply Buses". IEEE Proc. International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), pp. 1-6 (2014)

 F-J Ferrández-Pastor, J_M García-Chamizo, M. Nieto-Hidalgo, V. Romacho-Agud, F. Flórez-Revuelta. "Using Wavelet Transform to Disaggregate Electrical Power Consumption into the Major End-Uses". Ubiquitous Computing and Ambient Intelligence. Personalisation and User Adapted Services Lecture Notes in Computer Science, Vol. 8867, pp 272-279 (2014)

 Xu, Yizheng, and J. V. Milanovic. "Artificial-Intelligence-Based Methodology for Load Disaggregation at Bulk Supply Point." IEEE Transactions on Power Systems, pp( 99):1-9 (2014).

 S.Makonin, F.Popowich, "Nonintrusive load monitoring (NILM) performance evaluation", Energy Efficiency, (on-line since: 31 Oct 2014).

 M. Singh, S.Kumar, S. Semwal, R. S. Prasad, "Residential Load Signature Analysis for Their Segregation Using Wavelet—SVM", Power Electronics and Renewable Energy Systems, Lecture Notes in Electrical Engineering Volume 326, 2015, pp 863-871, (on-line since 20 Nov 2014)

 Piotr BILSKI, Krzysztof LISZEWSKI, Wieslaw WINIECKI, "Review and prospects of artificial intelligence applications in non-invasive identification of its electricity", Politechnika Warszawska, Instytut Radioelektroniki, ISSN 0033-2097, R. 90 NR 11/2014 , doi:10.12915/pe.2014.11.03

 Ridi, A.; Gisler, C.; Hennebert, J., "Appliance and state recognition using Hidden Markov Models," Data Science and Advanced Analytics (DSAA), 2014 International Conference on, pp.270-276. 2014.

 Gillman, M.D. and Donnal, J.S. and Paris, J. and Leeb, S.B. and El Sayed, M.A.H. and Wertz, K. and Schertz, S., "Energy Accountability Using Nonintrusive Load Monitoring", Sensors Journal, IEEE, 14(6):1923-1931, 2014, doi=10.1109/JSEN.2014.2305911

 Lanzisera, S. and Weber, A.R. and Liao, A. and Pajak, D. and Meier, A.K., "Communicating Power Supplies: Bringing the Internet to the Ubiquitous Energy Gateways of Electronic Devices", Internet of Things Journal, IEEE, 1(2):153-160, 2014, doi=10.1109/JIOT.2014.2307077

 Ducange, P. and Marcelloni, F. and Antonelli, M., "A Novel Approach Based on Finite-State Machines with Fuzzy Transitions for Nonintrusive Home Appliance Monitoring", IEEE Transactions on Industrial Informatics, 10(2):1185-1197, 2014, doi=10.1109/TII.2014.2304781

 Seyed Mostafa Tabatabaei, "Decomposition Techniques for Non-intrusive Home Appliance Load Monitoring",
Master Thesis in, Energy Systems-Electrical and Computer Engineering,
Spring 2014, University of Alberta, Canada.

 Bilski, P., Liszewski, K., Winiecki, W. Przegl?d i perspektywy zastosowa? sztucznej inteligencji w nieinwazyjnej identyfikacji odbiorników energii elektrycznej. Przegl?d Elektrotechniczny, 90(11):11-15, 2014 (in Polish)

Year 2013 : 3 citations

 On the Regularization Parameter Selection for Sparse Code Learning in Electrical Source Separation
M Figueiredo, B Ribeiro, AM de Almeida - Adaptive and Natural …, 2013 - Springer

 Sungnam Lee and Mengliev, S. and Yohan Chon and Rhan Ha and Hojung Cha, "Autonomous Construction of a Mountain Terrain Map Using Low-Cost Sensors and Group Information", Military Communications Conference, MILCOM 2013 - 2013 IEEE, Nov, 328-333, 2013, doi=0.1109/MILCOM.2013.64

 Semwal, S.; Joshi, D.; Prasad, R. S.; Raveendhra, D.; "The practicability of ICA in home appliances load profile separation using current signature: A preliminary study," Proc. of Intl. Conf. on Power, Energy and Control (ICPEC), 2013, pp.756-759, 2013