Scattering Transform for Classification in Non-Intrusive Load Monitoring

Everton Luiz de Aguiar, André Eugenio Lazzaretti, Bruna Machado Mulinari and Daniel Rodrigues Pipa
Additional contact information
Everton Luiz de Aguiar: CPGEI—Graduate Program in Electrical and Computer Engineering, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, PR, Brazil
André Eugenio Lazzaretti: CPGEI—Graduate Program in Electrical and Computer Engineering, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, PR, Brazil
Bruna Machado Mulinari: Dataplai, Eng. Niepce da Silva, 200, Curitiba 80610-280, PR, Brazil
Daniel Rodrigues Pipa: CPGEI—Graduate Program in Electrical and Computer Engineering, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, PR, Brazil

Energies, 2021, vol. 14, issue 20, 1-20

Abstract: Nonintrusive Load Monitoring (NILM) uses computational methods to disaggregate and classify electrical appliances signals. The classification is usually based on the power signatures of the appliances obtained by a feature extractor. State-of-the-art results were obtained extracting NILM features with convolutional neural networks (CNN). However, it depends on the training process with large datasets or data augmentation strategies. In this paper, we propose a feature extraction strategy for NILM using the Scattering Transform (ST). The ST is a convolutional network analogous to CNN. Nevertheless, it does not need a training process in the feature extraction stage, and the filter coefficients are analytically determined (not empirically, like CNN). We perform tests with the proposed method on different publicly available datasets and compare the results with state-of-the-art deep learning-based and traditional approaches (including wavelet transform and V-I representations). The results show that ST classification accuracy is more robust in terms of waveform parameters, such as signal length, sampling frequency, and event location. Besides, ST overcame the state-of-the-art techniques for single and aggregated loads (accuracies above 99% for all evaluated datasets), in different training scenarios with single and aggregated loads, indicating its feasibility in practical NILM scenarios.

Keywords: scattering transform; NILM features; features extractor (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/20/6796/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/20/6796/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:14:y:2021:i:20:p:6796-:d:658887

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().