Thresholding methods in non-intrusive load monitoring

Gómez Ullate, David; Precioso, Daniel

Publication:
Thresholding methods in non-intrusive load monitoring

dc.contributor.author	Gómez Ullate, David
dc.contributor.author	Precioso, Daniel
dc.contributor.ror	https://ror.org/02jjdwm75
dc.date.accessioned	2025-02-18T13:21:37Z
dc.date.available	2025-02-18T13:21:37Z
dc.date.issued	2023-04-01
dc.description.abstract	Non-intrusive load monitoring (NILM) is the problem of predicting the status or consumption of individual domestic appliances only from the knowledge of the aggregated power load. NILM is often formulated as a classification (ON/OFF) problem for each device. However, the training datasets gathered by smart meters do not contain these labels, but only the electric consumption at every time interval. This paper addresses a fundamental methodological problem in how a NILM problem is posed, namely how the different possible thresholding methods lead to different classification problems. Standard datasets and NILM deep learning models are used to illustrate how the choice of thresholding method affects the output results. Some criteria that should be considered for the choice of such methods are also proposed. Finally, we propose a slight modification to current deep learning models for multi-tasking, i.e. tackling the classification and regression problems simultaneously. Transfer learning between both problems might improve performance on each of them.
dc.description.peerreviewed	yes
dc.description.status	Published
dc.format	application/pdf
dc.identifier.citation	Precioso, D., & Gómez-Ullate, D. (2023). Thresholding methods in non-intrusive load monitoring. The Journal of Supercomputing, 79(13), 14039-14062. https://doi.org/10.1007/s11227-023-05149-8.
dc.identifier.doi	https://doi.org/10.1007/s11227-023-05149-8
dc.identifier.issn	14039–14062
dc.identifier.uri	https://hdl.handle.net/20.500.14417/3565
dc.journal.title	The Journal of Supercomputing
dc.language.iso	en
dc.page.final	14062
dc.page.initial	14039
dc.page.total	24
dc.publisher	Springer Nature Link
dc.relation.department	Applied Mathematics
dc.relation.entity	IE University
dc.relation.school	IE School of Science & Technology
dc.rights	Attribution 4.0 International
dc.rights.accessRights	info:eu-repo/semantics/openAccess
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/deed
dc.subject.keyword	Non-intrusive load monitoring (NILM)
dc.subject.keyword	Recurrent neural networks
dc.subject.keyword	Convolutional neural networks
dc.subject.keyword	Binary cross-entropy loss
dc.subject.keyword	Mean squared error loss
dc.title	Thresholding methods in non-intrusive load monitoring
dc.type	info:eu-repo/semantics/article
dc.version.type	info:eu-repo/semantics/publishedVersion
dc.volume.number	79
dspace.entity.type	Publication
relation.isAuthorOfPublication	d0525f43-b84b-4613-9984-4324ddf81556
relation.isAuthorOfPublication.latestForDiscovery	d0525f43-b84b-4613-9984-4324ddf81556