A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements

The central problems of some of the existing Non-Intrusive Load Monitoring (NILM) algorithms are indicated as: (1) higher required electrical device identification accuracy; (2) the fact that they enable training over a larger device count; and (3) their ability to be trained faster, limiting them f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Netzah Calamaro, Moshe Donko, Doron Shmilovitz
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	KDE—kernel density estimation GMM—Gaussian mixture model KNN—K-nearest neighbor NILM—nonintrusive load monitoring PCA—principal component analysis NIS—network information system Technology T
Acceso en línea:	https://doaj.org/article/498634edcd114e9c8e0574c058a5dcb0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:498634edcd114e9c8e0574c058a5dcb0
record_format	dspace
spelling	oai:doaj.org-article:498634edcd114e9c8e0574c058a5dcb02021-11-11T16:07:43ZA Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements10.3390/en142174101996-1073https://doaj.org/article/498634edcd114e9c8e0574c058a5dcb02021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7410https://doaj.org/toc/1996-1073The central problems of some of the existing Non-Intrusive Load Monitoring (NILM) algorithms are indicated as: (1) higher required electrical device identification accuracy; (2) the fact that they enable training over a larger device count; and (3) their ability to be trained faster, limiting them from usage in industrial premises and external grids due to their sensitivity to various device types found in residential premises. The algorithm accuracy is higher compared to previous work and is capable of training over at least thirteen electrical devices collaboratively, a number that could be much higher if such a dataset is generated. The algorithm trains the data around <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.8</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mn>8</mn></msup></mrow></semantics></math></inline-formula> faster due to a higher sampling rate. These improvements potentially enable the algorithm to be suitable for future “grids and industrial premises load identification” systems. The algorithm builds on new principles: an electro-spectral features preprocessor, a faster waveform sampling sensor, a shorter required duration for the recorded data set, and the use of current waveforms vs. energy load profile, as was the case in previous NILM algorithms. Since the algorithm is intended for operation in any industrial premises or grid location, fast training is required. Known classification algorithms are comparatively trained using the proposed preprocessor over residential datasets, and in addition, the algorithm is compared to five known low-sampling NILM rate algorithms. The proposed spectral algorithm achieved 98% accuracy in terms of device identification over two international datasets, which is higher than the usual success of NILM algorithms.Netzah CalamaroMoshe DonkoDoron ShmilovitzMDPI AGarticleKDE—kernel density estimationGMM—Gaussian mixture modelKNN—K-nearest neighborNILM—nonintrusive load monitoringPCA—principal component analysisNIS—network information systemTechnologyTENEnergies, Vol 14, Iss 7410, p 7410 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	KDE—kernel density estimation GMM—Gaussian mixture model KNN—K-nearest neighbor NILM—nonintrusive load monitoring PCA—principal component analysis NIS—network information system Technology T
spellingShingle	KDE—kernel density estimation GMM—Gaussian mixture model KNN—K-nearest neighbor NILM—nonintrusive load monitoring PCA—principal component analysis NIS—network information system Technology T Netzah Calamaro Moshe Donko Doron Shmilovitz A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements
description	The central problems of some of the existing Non-Intrusive Load Monitoring (NILM) algorithms are indicated as: (1) higher required electrical device identification accuracy; (2) the fact that they enable training over a larger device count; and (3) their ability to be trained faster, limiting them from usage in industrial premises and external grids due to their sensitivity to various device types found in residential premises. The algorithm accuracy is higher compared to previous work and is capable of training over at least thirteen electrical devices collaboratively, a number that could be much higher if such a dataset is generated. The algorithm trains the data around <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.8</mn><mo>×</mo><msup><mrow><mn>10</mn></mrow><mn>8</mn></msup></mrow></semantics></math></inline-formula> faster due to a higher sampling rate. These improvements potentially enable the algorithm to be suitable for future “grids and industrial premises load identification” systems. The algorithm builds on new principles: an electro-spectral features preprocessor, a faster waveform sampling sensor, a shorter required duration for the recorded data set, and the use of current waveforms vs. energy load profile, as was the case in previous NILM algorithms. Since the algorithm is intended for operation in any industrial premises or grid location, fast training is required. Known classification algorithms are comparatively trained using the proposed preprocessor over residential datasets, and in addition, the algorithm is compared to five known low-sampling NILM rate algorithms. The proposed spectral algorithm achieved 98% accuracy in terms of device identification over two international datasets, which is higher than the usual success of NILM algorithms.
format	article
author	Netzah Calamaro Moshe Donko Doron Shmilovitz
author_facet	Netzah Calamaro Moshe Donko Doron Shmilovitz
author_sort	Netzah Calamaro
title	A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements
title_short	A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements
title_full	A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements
title_fullStr	A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements
title_full_unstemmed	A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements
title_sort	highly accurate nilm: with an electro-spectral space that best fits algorithm’s national deployment requirements
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/498634edcd114e9c8e0574c058a5dcb0
work_keys_str_mv	AT netzahcalamaro ahighlyaccuratenilmwithanelectrospectralspacethatbestfitsalgorithmsnationaldeploymentrequirements AT moshedonko ahighlyaccuratenilmwithanelectrospectralspacethatbestfitsalgorithmsnationaldeploymentrequirements AT doronshmilovitz ahighlyaccuratenilmwithanelectrospectralspacethatbestfitsalgorithmsnationaldeploymentrequirements AT netzahcalamaro highlyaccuratenilmwithanelectrospectralspacethatbestfitsalgorithmsnationaldeploymentrequirements AT moshedonko highlyaccuratenilmwithanelectrospectralspacethatbestfitsalgorithmsnationaldeploymentrequirements AT doronshmilovitz highlyaccuratenilmwithanelectrospectralspacethatbestfitsalgorithmsnationaldeploymentrequirements
_version_	1718432410318667776

A Highly Accurate NILM: With an Electro-Spectral Space That Best Fits Algorithm’s National Deployment Requirements

Ejemplares similares