Abstract
Non-intrusive load monitoring (NILM) is a technology that analyzes total electricity consumption data to determine whether a specific type of residential appliance is operated. However, despite many previous studies conducted in this field, NILM is still limited to develo** models in the form of regression and presenting relative performance results. However, to be used in commercial applications, it must be finally developed as a classification model to present the absolute performance results from the service viewpoint. In this paper, a new methodology is proposed to build a pre-trained NILM model that ensures reliable classification performance, whereby differentiated steps are adopted to improve NILM accuracy. In particular, the methodology includes an intelligent result processing scheme that accurately identifies appliance activation based on past profiles and translates the NILM results into proper information for service utilization, which has not been addressed in previous studies. The developed pre-trained NILM model can be used to detect appliance activation to indirectly monitor the activity of daily living (ADL) of single-person households in social safety net services as a vital sign. The detailed explanation and experimental results are presented as reference to build a pre-trained NILM model in many domains.
Similar content being viewed by others
Availability of data and materials
All data analysed during this study are included in [38].
Code Availability
Related source codes are available at https://github.com/gyubaekkim/new_nilm/
References
Green Button Alliance (2022) https://www.greenbuttonalliance.org/about#who. Accessed 30 April 2022
Sense (2022) https://sense.com. Accessed 30 April 2022
Smappee (2022) https://www.smappee.com. Accessed 30 April 2022
ENCORED Enertalk (2022) https://www.enertalk.com/product. Accessed 30 April 2022
Hart G (1992) Nonintrusive appliance load monitoring. The IEEE 80(12):1870–1892. https://doi.org/10.1109/5.192069
Shin C, Rho S et al (2019) Data requirements for applying machine learning to energy disaggregation. Energies 12(9):1696. https://doi.org/10.3390/en12091696
Zhuang M, Shahidehpour M, Li Z (2019) An overview of non-intrusive load monitoring: approaches, business applications, and challenges. In: International conference on power system technology. https://doi.org/10.1109/POWERCON.2018.8601534
Nation J, Aboulian A et al (2017) Nonintrusive monitoring for shipboard fault detection. IEEE Sensors Applications Symposium (SAS). https://doi.org/10.1109/SAS.2017.7894029
Smappee (2022) Blog. https://www.smappee.com/blog/smappee-appliance-recognition. Accessed 30 April 2022
Batra N, Kelly J et al (2014) NILMTK: An open source toolkit for non-intrusive load monitoring. In: International conference on future energy systems (ACM e-Energy). https://doi.org/10.1145/2602044.2602051
Long W, Chen L, Li X (2016) A framework of energy disaggregation based on adaptive association rules mining. In: International conference on energy, materials and manufacturing engineering (EMME). https://doi.org/10.12783/dtetr/emme2016/9790
Dantas P, Junior W, Carvalho C (2020) Energy Disaggregation Using Principal Component Analysis Representation. In: International conference on machine learning and intelligent systems (MLIS). https://doi.org/10.3233/FAIA200766
Elhamifar E, Sastry S (2015) Energy disaggregation via learning Powerlets and sparse coding. In: AAAI conference on artificial intelligence, pp 629–635
Tomkins S, Pujara J, Getoor L (2017) Disambiguating energy disaggregation: a collective probabilistic approach. In: International joint conference on artificial intelligence (IJCAI), pp 2857–2863
Huang X, Yin B, et al. (2019) An online non-intrusive load monitoring method based on Hidden Markov model. J Phys 1176(4). https://doi.org/10.1088/1742-6596/1176/4/042036
Neural Disaggregator (2022) https://github.com/OdysseasKr/neural-disaggregator. Accessed 30 April 2022
Teixeira R, Antunes M, Gomes D (2021) Using deep learning and knowledge transfer to disaggregate energy consumption. In: International conference on wavelet analysis and pattern recognition (ICWAPR). https://doi.org/10.1109/ICWAPR54887.2021.9736149
Shastri H, Batra N (2021) Neural network approaches and dataset parser for NILM toolkit. In: ACM international conference on systems for energy-efficient buildings, cities, and transportation, pp 172–175. https://doi.org/10.1145/3486611.3486652
Nguyen K, Dekneuvel E et al (2014) Event Detection and Disaggregation Algorithms for NIALM System. International Workshop on Non-Intrusive Load Monitoring (NILM)
Garcia F, Souza W et al (2020) NILM-based approach for energy efficiency assessment of household appliances. Energy Informatics. https://doi.org/10.1186/s42162-020-00131-7
Kelati A, Gaber H et al (2020) Implementation of non-intrusive appliances load monitoring (NIALM) on k-nearest neighbors (k-NN) classifier. AIMS Electronics and Electrical Engineering 4(3):326–344. https://doi.org/10.3934/ElectrEng.2020.3.326
Puente C, Palacios R et al (2020) Non-Intrusive Load monitoring (NILM) for energy disaggregation using soft computing techniques. Energies 13(12):3117. https://doi.org/10.3390/en13123117
Liu Y, Wang Y et al (2021) Toward robust Non-Intrusive load monitoring via probability model framed ensemble method. Sensors 21(21):7272. https://doi.org/10.3390/s21217272
Gopinath R, Kumar M et al (2020) Energy management using non-intrusive load monitoring techniques – State-of-the-art and future research directions. Sustainable Cities and Society 62:102411. https://doi.org/10.1016/j.scs.2020.102411
Patrick H, Calatroni A et al (2021) Review on deep neural networks applied to Low-Frequency NILM. Energies 14(9):2390. https://doi.org/10.3390/en14092390
Kohl T, Kellner D, Mihale-Wilson C (2021) Semi-supervised energy disaggregation for real-world adoption. European Conference on Information Systems (ECIS)
Armel C, Gupta A et al (2013) Is disaggregation the holy grail of energy efficiency? the case of electricity. Energy Policy 52:213–234. https://doi.org/10.1016/j.enpol.2012.08.062
Kelly J, Knottenbelt W (2015) Neural NILM: deep neural networks applied to energy disaggregation. In: ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, pp 55–64. https://doi.org/10.1145/2821650.2821672
Rehman A, Lie T et al (2021) Comparative evaluation of machine learning models and input feature space for non-intrusive load monitoring. Modern Power Systems and Clean Energy 9(5):1161–1171. https://doi.org/10.35833/MPCE.2020.000741
Hinterstocker M, Schott P, Roon S (2017) Disaggregation of household load profiles. International energy industry conference
Angelis G, Timplalexis C et al (2022) NILM Applications: Literature review of learning approaches, recent developments and challenges. Energy and Buildings 261:111951. https://doi.org/10.1016/j.enbuild.2022.111951
Joshi H, Parikh A, Shah S (2021) A Different Neural NILM based Energy Disaggregation. International Research Journal of Engineering and Technology (IRJET)
Kolter J, Johnson M (2011) REDD: A public data set for energy disaggregation research. The SustKDD workshop on Data Mining Applications in Sustainability 25:59–62
Barker S, Mishra A et al (2012) Smart*: An Open Data Set and Tools for Enabling Research in Sustainable Homes. The SustKDD workshop on Data Mining Applications in Sustainability
Batra N, Gulati M, et al. (2013) It’s different: Insights into home energy consumption in India. ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings, pp 1–8. https://doi.org/10.1145/2528282.2528293
Monacchi A, Egarter D et al (2014) GREEND: An energy consumption dataset of households in Italy and Austria. In: IEEE international conference on smart grid communications (SmartGridComm). https://doi.org/10.1109/SmartGridComm.2014.7007698
Kelly J, Knottenbelt W (2015) The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific Data 2:150007. https://doi.org/10.1038/sdata.2015.7
Shin C, Lee E et al (2019) The ENERTALK dataset, 15 Hz electricity consumption data from 22 houses in Korea. Scientific Data 6:193. https://doi.org/10.1038/s41597-019-0212-5
Gu Y, Chen Q et al (2019) GAN-based model for residential load generation considering typical consumption patterns. IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT) . https://doi.org/10.1109/ISGT.2019.8791575
Fekri M, Ghosh A, Grolinger K (2019) Generating energy data for machine learning with recurrent generative adversarial networks. Energies 13(1):130. https://doi.org/10.3390/en13010130
Hossenini S, Kelouwani S et al (2017) A semi-synthetic dataset development tool for household energy consumption analysis. In: IEEE international conference on industrial technology (ICIT). https://doi.org/10.1109/ICIT.2017.7915420
Delfosse A, Hebrail G, Zerroug A (2020) Deep learning applied to NILM: is data augmentation worth for energy disaggregation?. In: European conference on artificial intelligence (ECAI), pp 2972–2977. https://doi.org/10.3233/FAIA200471
The HDF Group (2022) https://www.hdfgroup.org. Accessed 30 April 2022
NILMTK (2022) Open Source NILM Toolkit. https://nilmtk.github.io. Accessed 30 April 2022
Wang L, Mao S et al (2022) Pre-Trained Models for Non-Intrusive appliance load monitoring. IEEE Transactions on Green Communications and Networking 6(1):56–68. https://doi.org/10.1109/TGCN.2021.3087702
D’Incecco M, Squartini S, Zhong M (2020) Transfer learning for Non-Intrusive load monitoring. IEEE Trans Smart Grid 11(2):1419–1429. https://doi.org/10.1109/TSG.2019.2938068
Yang M, Yue L, Liu A (2021) Nonintrusive residential electricity load decomposition based on transfer learning. Sustainability 13(12):6546. https://doi.org/10.3390/su13126546
Kukunuri R, Aglawe A et al (2020) EdgeNILM: Towards NILM on Edge devices. In: ACM international conference on systems for energy-efficient buildings, cities, and transportation, pp 90–99. https://doi.org/10.1145/3408308.3427977
Biansoongnern S, Boonyang P (2022) An alternative Low-Cost embedded NILM system for household energy conservation with a low sampling rate. Symmetry 14(2):279. https://doi.org/10.3390/sym14020279
Zhang Y, Tang G et al (2022) FedNILM: Applying Federated Learning to NILM Applications at the Edge. IEEE Transactions on Green Communications and Networking. https://doi.org/10.1109/TGCN.2022.3167392
Roux N, Vrigneau B, Sentieys O (2019) Improving NILM by Combining Sensor Data and Linear Programming. IEEE Sensors Applications Symposium (SAS). https://doi.org/10.1109/SAS.2019.8706021
Franco P, Martínez J, et al. (2021) Iot based approach for load monitoring and activity recognition in smart homes. IEEE Access 9:45325–45339. https://doi.org/10.1109/ACCESS.2021.3067029
Dai S, Wang Q, Meng F (2021) A telehealth framework for dementia care: an ADLs patterns recognition model for patients based on NILM. In: International joint conference on neural networks (IJCNN). https://doi.org/10.1109/IJCNN52387.2021.9534058
Marino C, Masquil E et al (2021) NILM: Multivariate DNN performance analysis with high frequency features. IEEE PES Innovative Smart Grid Technologies Conference. https://doi.org/10.1109/ISGTLatinAmerica52371.2021.9543016
Timplalexis C, Angelis G et al (2022) Low frequency residential non-intrusive load monitoring based on a hybrid feature extraction tree-learning approach. Energy Sources 44:493–514. https://doi.org/10.1080/15567036.2022.2046663
Kruskall J, Liberman M (1983) The symmetric time war** problem: from continuous to discrete. Time warps string edits and macromolecules: the theory and practice of sequence comparison. Addison-Wesley, Massachusetts, pp 125–161
Rehmani M, Saad S, et al. (2021) Power profile and thresholding assisted Multi-Label NILM classification. Energies 14(22):7609. https://doi.org/10.3390/en14227609
Kumar G, Shuib B et al (2021) Data harmonization for heterogeneous datasets: a systematic literature review. Appl Sci 11(17):8275. https://doi.org/10.3390/app11178275
Read J, Pfahringer B et al (2009) Classifier chains for multi-label classification. Mach Learn 85(3):254–269. https://doi.org/10.1007/978-3-642-04174-7_17
Kim G, Park S (2021) Activity detection from electricity consumption and communication usage data for monitoring lonely deaths. Sensors 21(9):3016. https://doi.org/10.3390/s21093016
MLJAR (2022) https://github.com/mljar/website_snippets/blob/master/how_many_trees. Accessed 30 April 2022
Funding
This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (IITP-2017-0-00477, (SW starlab) Research and development of the high performance in-memory distributed DBMS based on flash memory storage in IoT environment).
Author information
Authors and Affiliations
Contributions
Not applicable.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for Publication
Not applicable.
Conflict of Interests
Not applicable.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kim, G., Park, S. Pre-trained non-intrusive load monitoring model for recognizing activity of daily living. Appl Intell 53, 10937–10955 (2023). https://doi.org/10.1007/s10489-022-04053-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04053-7