A Siamese CNN + KNN-Based Classification Framework for Non-intrusive Load Monitoring

Ferraz, Filipe C.; Monteiro, Raul V. A.; Teixeira, Raoni F. S.; Bretas, Arturo S.

doi:10.1007/s40313-023-00999-2

Title: A Siamese CNN + KNN-Based Classification Framework for Non-intrusive Load Monitoring

Journal Article · 01 May 2023 · Journal of Control, Automation and Electrical Systems

DOI: https://doi.org/10.1007/s40313-023-00999-2 · OSTI ID:1972322

Ferraz, Filipe C. ^[1];

^[1]; Teixeira, Raoni F. S. ^[1];

^[2]

Federal University of Mato Grosso (Brazil)
Univ. of Florida, Gainesville, FL (United States); Pacific Northwest National Lab. (PNNL), Richland, WA (United States)

Through the development of smart grids, programs such as demand side response, have been presented as auxiliary services to the real-time operation of distributed networks. In order to provide consumers information on their energy consumption, so that a modulation in consumption is possible, non-intrusive load monitoring has been introduced as an solution to this pattern recognition problem. Non-intrusive load monitoring enables the modeling of electrical loads connected to the low-voltage system, considering only a single measurement point. Presented state-of-the-art solutions though, consider availability of data as well as representation of all possible classes of the environment. This is of course a most conservative hypothesis, since in real-life applications availability of such data is much difficult, as well as the dynamic behavior of models is implicitly evolving in time. Here, a framework that uses neural Siamese networks with k-nearest neighbor clustering is presented toward non-intrusive load monitoring. Online learning feature is implemented, which relaxes the hypothesis of data requirements as well addresses the evolving nature of load profile. k-nearest clustering allows nonlinear characteristic space modelling. Test results using synthetics and real-life data show that the solution, besides obtaining a good generalizability in the classification, also obtained results with an accuracy of 95.77%.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Sponsoring Organization:: USDOE; National Council for Scientific and Technological Development (CNPq)

Grant/Contract Number:: AC05-76RL01830; 409687/2018–9

OSTI ID:: 1972322

Report Number(s):: PNNL-SA-184783

Journal Information:: Journal of Control, Automation and Electrical Systems, Vol. 34, Issue 4; ISSN 2195-3880

Publisher:: SpringerCopyright Statement

Country of Publication:: United States

Language:: English

References (36)

Multi-objective evolutionary algorithms applied to non-intrusive load monitoring Li, Ling; Yang, Liyu; Chen, Hao Electric Power Systems Research, Vol. 177 https://doi.org/10.1016/j.epsr.2019.105961	journal	December 2019
New Design of a Supervised Energy Disaggregation Model Based on the Deep Neural Network for a Smart Grid ÇAvdar, İsmail; Faryad, Vahid Energies, Vol. 12, Issue 7 https://doi.org/10.3390/en12071217	journal	March 2019
A Hybrid Signature-based Iterative Disaggregation algorithm for Non-Intrusive Load Monitoring Cominola, A.; Giuliani, M.; Piga, D. Applied Energy, Vol. 185 https://doi.org/10.1016/j.apenergy.2016.10.040	journal	January 2017
A NILM algorithm with enhanced disaggregation scheme under harmonic current vectors Bouhouras, Aggelos S.; Gkaidatzis, Paschalis A.; Panagiotou, Evangelos Energy and Buildings, Vol. 183 https://doi.org/10.1016/j.enbuild.2018.11.013	journal	January 2019
A Cloud-Based On-Line Disaggregation Algorithm for Home Appliance Loads Mengistu, Million Abayneh; Girmay, Awet Abraha; Camarda, Chirstian IEEE Transactions on Smart Grid, Vol. 10, Issue 3 https://doi.org/10.1109/TSG.2018.2826844	journal	May 2019
Toward Open Set Recognition Scheirer, W. J.; de Rezende Rocha, A.; Sapkota, A. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, Issue 7 https://doi.org/10.1109/TPAMI.2012.256	journal	July 2013
Non-intrusive load monitoring by using active and reactive power in additive Factorial Hidden Markov Models Bonfigli, Roberto; Principi, Emanuele; Fagiani, Marco Applied Energy, Vol. 208 https://doi.org/10.1016/j.apenergy.2017.08.203	journal	December 2017
Online end-use energy disaggregation via jump linear models Breschi, Valentina; Piga, Dario; Bemporad, Alberto Control Engineering Practice, Vol. 89 https://doi.org/10.1016/j.conengprac.2019.05.011	journal	August 2019
Multi-Label Classification Based on Random Forest Algorithm for Non-Intrusive Load Monitoring System Wu, Xin; Gao, Yuchen; Jiao, Dian Processes, Vol. 7, Issue 6 https://doi.org/10.3390/pr7060337	journal	June 2019
Review on Deep Neural Networks Applied to Low-Frequency NILM Huber, Patrick; Calatroni, Alberto; Rumsch, Andreas Energies, Vol. 14, Issue 9 https://doi.org/10.3390/en14092390	journal	April 2021
Nonintrusive appliance load monitoring Hart, G. W. Proceedings of the IEEE, Vol. 80, Issue 12 https://doi.org/10.1109/5.192069	journal	January 1992
Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network Liu, Chao; Akintayo, Adedotun; Jiang, Zhanhong Applied Energy, Vol. 211 https://doi.org/10.1016/j.apenergy.2017.12.026	journal	February 2018
Load Identification and Classification of Activities of Daily Living using Residential Smart Meter Data Devlin, Michael A.; Hayes, Barry P. 2019 IEEE Milan PowerTech https://doi.org/10.1109/PTC.2019.8810455	conference	June 2019
Standardization and Its Effects on K-Means Clustering Algorithm Mohamad, Ismail Bin; Usman, Dauda Research Journal of Applied Sciences, Engineering and Technology, Vol. 6, Issue 17 https://doi.org/10.19026/rjaset.6.3638	journal	September 2013
Non-intrusive Load Composition Estimation from Aggregate ZIP Load Models using Machine Learning Asres, Mulugeta W.; Girmay, Awet A.; Camarda, Christian International Journal of Electrical Power & Energy Systems, Vol. 105 https://doi.org/10.1016/j.ijepes.2018.08.016	journal	February 2019
Adaptive on-line unsupervised appliance modeling for autonomous household database construction Hosseini, Sayed Saeed; Kelouwani, Sousso; Agbossou, Kodjo International Journal of Electrical Power & Energy Systems, Vol. 112 https://doi.org/10.1016/j.ijepes.2019.04.034	journal	November 2019
Speech Emotion Recognition via Contrastive Loss under Siamese Networks Lian, Zheng; Li, Ya; Tao, Jianhua MM '18: ACM Multimedia Conference, Proceedings of the Joint Workshop of the 4th Workshop on Affective Social Multimedia Computing and first Multi-Modal Affective Computing of Large-Scale Multimedia Data https://doi.org/10.1145/3267935.3267946	conference	October 2018
A voltage and current measurement dataset for plug load appliance identification in households Medico, Roberto; De Baets, Leen; Gao, Jingkun Scientific Data, Vol. 7, Issue 1 https://doi.org/10.1038/s41597-020-0389-7	journal	February 2020
Appliance Classification by Power Signal Analysis Based on Multi-Feature Combination Multi-Layer LSTM Kim, Jin-Gyeom; Lee, Bowon Energies, Vol. 12, Issue 14 https://doi.org/10.3390/en12142804	journal	July 2019
Open-set Face Recognition for Small Galleries Using Siamese Networks Salomon, Gabriel; Britto, Alceu; Vareto, Rafael H. 2020 International Conference on Systems, Signals and Image Processing (IWSSIP) https://doi.org/10.1109/IWSSIP48289.2020.9145245	conference	July 2020
Nonintrusive appliance load monitoring: Review and outlook Zeifman, Michael; Roth, Kurt IEEE Transactions on Consumer Electronics, Vol. 57, Issue 1 https://doi.org/10.1109/TCE.2011.5735484	journal	February 2011
Feature Extraction-Based Hellinger Distance Algorithm for Nonintrusive Aging Load Identification in Residential Buildings Chang, Hsueh-Hsien; Lee, Meng-Chien; Lee, Wei-Jen IEEE Transactions on Industry Applications, Vol. 52, Issue 3 https://doi.org/10.1109/TIA.2016.2533487	journal	May 2016
An Extensible Approach for Non-Intrusive Load Disaggregation With Smart Meter Data Kong, Weicong; Dong, Zhao Yang; Ma, Jin IEEE Transactions on Smart Grid, Vol. 9, Issue 4 https://doi.org/10.1109/TSG.2016.2631238	journal	July 2018
Revisiting kd-tree for Nearest Neighbor Search Ram, Parikshit; Sinha, Kaushik Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining https://doi.org/10.1145/3292500.3330875	conference	July 2019
MO-NILM: A multi-objective evolutionary algorithm for NILM classification Machlev, Ram; Belikov, Juri; Beck, Yuval Energy and Buildings, Vol. 199 https://doi.org/10.1016/j.enbuild.2019.06.046	journal	September 2019
Detection of unidentified appliances in non-intrusive load monitoring using siamese neural networks De Baets, Leen; Develder, Chris; Dhaene, Tom International Journal of Electrical Power & Energy Systems, Vol. 104 https://doi.org/10.1016/j.ijepes.2018.07.026	journal	January 2019
Non-intrusive load monitoring under residential solar power influx Dinesh, Chinthaka; Welikala, Shirantha; Liyanage, Yasitha Applied Energy, Vol. 205 https://doi.org/10.1016/j.apenergy.2017.08.094	journal	November 2017
Non-Intrusive Energy Disaggregation Using Non-Negative Matrix Factorization With Sum-to-k Constraint Rahimpour, Alireza; Qi, Hairong; Fugate, David IEEE Transactions on Power Systems, Vol. 32, Issue 6 https://doi.org/10.1109/TPWRS.2017.2660246	journal	November 2017
Deep Sparse Coding for Non–Intrusive Load Monitoring Singh, Shikha; Majumdar, Angshul IEEE Transactions on Smart Grid, Vol. 9, Issue 5 https://doi.org/10.1109/TSG.2017.2666220	journal	September 2018
Unsupervised algorithm for disaggregating low-sampling-rate electricity consumption of households Holweger, Jordan; Dorokhova, Marina; Bloch, Lionel Sustainable Energy, Grids and Networks, Vol. 19 https://doi.org/10.1016/j.segan.2019.100244	journal	September 2019
Non-intrusive load monitoring algorithm based on features of V–I trajectory Wang, A. Longjun; Chen, B. Xiaomin; Wang, C. Gang Electric Power Systems Research, Vol. 157 https://doi.org/10.1016/j.epsr.2017.12.012	journal	April 2018
Implementation of a robust real-time non-intrusive load monitoring solution Welikala, Shirantha; Thelasingha, Neelanga; Akram, Muhammed Applied Energy, Vol. 238 https://doi.org/10.1016/j.apenergy.2019.01.167	journal	March 2019
Real-time non-intrusive load monitoring: A light-weight and scalable approach Athanasiadis, Christos L.; Papadopoulos, Theofilos A.; Doukas, Dimitrios I. Energy and Buildings, Vol. 253 https://doi.org/10.1016/j.enbuild.2021.111523	journal	December 2021
A hybrid model for appliance classification based on time series features Liu, Hui; Wu, Haiping; Yu, Chenming Energy and Buildings, Vol. 196 https://doi.org/10.1016/j.enbuild.2019.05.028	journal	August 2019
Non-Intrusive Energy Use Monitoring for a Group of Electrical Appliances Liu, Yu; Geng, Guangchao; Gao, Shan IEEE Transactions on Smart Grid, Vol. 9, Issue 4 https://doi.org/10.1109/TSG.2016.2643700	journal	July 2018
Simultaneous Detection of Multiple Appliances From Smart-Meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning Singhal, Vanika; Maggu, Jyoti; Majumdar, Angshul IEEE Transactions on Smart Grid, Vol. 10, Issue 3 https://doi.org/10.1109/TSG.2018.2815763	journal	May 2019