Power Profile and Thresholding Assisted Multi-Label NILM Classification

Next-generation power systems aim at optimizing the energy consumption of household appliances by utilising computationally intelligent techniques, referred to as load monitoring. Non-intrusive load monitoring (NILM) is considered to be one of the most cost-effective methods for load classification....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Muhammad Asif Ali Rehmani, Saad Aslam, Shafiqur Rahman Tito, Snjezana Soltic, Pieter Nieuwoudt, Neel Pandey, Mollah Daud Ahmed
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	non-intrusive load monitoring (NILM) machine learning smart building energy management systems (SBEM) multiclassification computational complexity energy efficiency Technology T
Acceso en línea:	https://doaj.org/article/fc21117175654e7c9b1f57342b74ab5e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fc21117175654e7c9b1f57342b74ab5e
record_format	dspace
spelling	oai:doaj.org-article:fc21117175654e7c9b1f57342b74ab5e2021-11-25T17:27:12ZPower Profile and Thresholding Assisted Multi-Label NILM Classification10.3390/en142276091996-1073https://doaj.org/article/fc21117175654e7c9b1f57342b74ab5e2021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/22/7609https://doaj.org/toc/1996-1073Next-generation power systems aim at optimizing the energy consumption of household appliances by utilising computationally intelligent techniques, referred to as load monitoring. Non-intrusive load monitoring (NILM) is considered to be one of the most cost-effective methods for load classification. The objective is to segregate the energy consumption of individual appliances from their aggregated energy consumption. The extracted energy consumption of individual devices can then be used to achieve demand-side management and energy saving through optimal load management strategies. Machine learning (ML) has been popularly used to solve many complex problems including NILM. With the availability of the energy consumption datasets, various ML algorithms have been effectively trained and tested. However, most of the current methodologies for NILM employ neural networks only for a limited operational output level of appliances and their combinations (i.e., only for a small number of classes). On the contrary, this work depicts a more practical scenario where over a hundred different combinations were considered and labelled for the training and testing of various machine learning algorithms. Moreover, two novel concepts—i.e., thresholding/occurrence per million (OPM) along with power windowing—were utilised, which significantly improved the performance of the trained algorithms. All the trained algorithms were thoroughly evaluated using various performance parameters. The results shown demonstrate the effectiveness of thresholding and OPM concepts in classifying concurrently operating appliances using ML.Muhammad Asif Ali RehmaniSaad AslamShafiqur Rahman TitoSnjezana SolticPieter NieuwoudtNeel PandeyMollah Daud AhmedMDPI AGarticlenon-intrusive load monitoring (NILM)machine learningsmart building energy management systems (SBEM)multiclassificationcomputational complexityenergy efficiencyTechnologyTENEnergies, Vol 14, Iss 7609, p 7609 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	non-intrusive load monitoring (NILM) machine learning smart building energy management systems (SBEM) multiclassification computational complexity energy efficiency Technology T
spellingShingle	non-intrusive load monitoring (NILM) machine learning smart building energy management systems (SBEM) multiclassification computational complexity energy efficiency Technology T Muhammad Asif Ali Rehmani Saad Aslam Shafiqur Rahman Tito Snjezana Soltic Pieter Nieuwoudt Neel Pandey Mollah Daud Ahmed Power Profile and Thresholding Assisted Multi-Label NILM Classification
description	Next-generation power systems aim at optimizing the energy consumption of household appliances by utilising computationally intelligent techniques, referred to as load monitoring. Non-intrusive load monitoring (NILM) is considered to be one of the most cost-effective methods for load classification. The objective is to segregate the energy consumption of individual appliances from their aggregated energy consumption. The extracted energy consumption of individual devices can then be used to achieve demand-side management and energy saving through optimal load management strategies. Machine learning (ML) has been popularly used to solve many complex problems including NILM. With the availability of the energy consumption datasets, various ML algorithms have been effectively trained and tested. However, most of the current methodologies for NILM employ neural networks only for a limited operational output level of appliances and their combinations (i.e., only for a small number of classes). On the contrary, this work depicts a more practical scenario where over a hundred different combinations were considered and labelled for the training and testing of various machine learning algorithms. Moreover, two novel concepts—i.e., thresholding/occurrence per million (OPM) along with power windowing—were utilised, which significantly improved the performance of the trained algorithms. All the trained algorithms were thoroughly evaluated using various performance parameters. The results shown demonstrate the effectiveness of thresholding and OPM concepts in classifying concurrently operating appliances using ML.
format	article
author	Muhammad Asif Ali Rehmani Saad Aslam Shafiqur Rahman Tito Snjezana Soltic Pieter Nieuwoudt Neel Pandey Mollah Daud Ahmed
author_facet	Muhammad Asif Ali Rehmani Saad Aslam Shafiqur Rahman Tito Snjezana Soltic Pieter Nieuwoudt Neel Pandey Mollah Daud Ahmed
author_sort	Muhammad Asif Ali Rehmani
title	Power Profile and Thresholding Assisted Multi-Label NILM Classification
title_short	Power Profile and Thresholding Assisted Multi-Label NILM Classification
title_full	Power Profile and Thresholding Assisted Multi-Label NILM Classification
title_fullStr	Power Profile and Thresholding Assisted Multi-Label NILM Classification
title_full_unstemmed	Power Profile and Thresholding Assisted Multi-Label NILM Classification
title_sort	power profile and thresholding assisted multi-label nilm classification
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/fc21117175654e7c9b1f57342b74ab5e
work_keys_str_mv	AT muhammadasifalirehmani powerprofileandthresholdingassistedmultilabelnilmclassification AT saadaslam powerprofileandthresholdingassistedmultilabelnilmclassification AT shafiqurrahmantito powerprofileandthresholdingassistedmultilabelnilmclassification AT snjezanasoltic powerprofileandthresholdingassistedmultilabelnilmclassification AT pieternieuwoudt powerprofileandthresholdingassistedmultilabelnilmclassification AT neelpandey powerprofileandthresholdingassistedmultilabelnilmclassification AT mollahdaudahmed powerprofileandthresholdingassistedmultilabelnilmclassification
_version_	1718412386318155776

Power Profile and Thresholding Assisted Multi-Label NILM Classification

Ejemplares similares