Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method

As a pivotal technological foundation for smart home implementation, non-intrusive load monitoring is emerging as a widely recognized and popular technology to replace the sensors or sockets networks for the detailed household appliance monitoring. In this paper, a probability model framed ensemble...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu Liu, Yan Wang, Yu Hong, Qianyun Shi, Shan Gao, Xueliang Huang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	dictionary learning ensemble method non-intrusive load monitoring probability model uncertainty analysis Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/02cf742d438c4c388305f9120634ca31
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:02cf742d438c4c388305f9120634ca31
record_format	dspace
spelling	oai:doaj.org-article:02cf742d438c4c388305f9120634ca312021-11-11T19:13:57ZToward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method10.3390/s212172721424-8220https://doaj.org/article/02cf742d438c4c388305f9120634ca312021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7272https://doaj.org/toc/1424-8220As a pivotal technological foundation for smart home implementation, non-intrusive load monitoring is emerging as a widely recognized and popular technology to replace the sensors or sockets networks for the detailed household appliance monitoring. In this paper, a probability model framed ensemble method is proposed for the target of robust appliance monitoring. Firstly, the non-intrusive load disaggregation-oriented ensemble architecture is presented. Then, dictionary learning model is utilized to formulate the individual classifier, while the sparse coding-based approach is capable of providing multiple solutions under greedy mechanism. Furthermore, a fully probabilistic model is established for combined classifier, where the candidate solutions are all labelled with probability scores and evaluated via two-stage decision-making. The proposed method is tested on both low-voltage network simulator platform and field measurement datasets, and the results show that the proposed ensemble method always guarantees an enhancement on the performance of non-intrusive load disaggregation. Besides, the proposed approach shows high flexibility and scalability in classification model selection. Therefore, by initializing the architecture and approach of ensemble method-based NILM, this work plays a pioneer role in using ensemble method to improve the robustness and reliability of non-intrusive appliance monitoring.Yu LiuYan WangYu HongQianyun ShiShan GaoXueliang HuangMDPI AGarticledictionary learningensemble methodnon-intrusive load monitoringprobability modeluncertainty analysisChemical technologyTP1-1185ENSensors, Vol 21, Iss 7272, p 7272 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	dictionary learning ensemble method non-intrusive load monitoring probability model uncertainty analysis Chemical technology TP1-1185
spellingShingle	dictionary learning ensemble method non-intrusive load monitoring probability model uncertainty analysis Chemical technology TP1-1185 Yu Liu Yan Wang Yu Hong Qianyun Shi Shan Gao Xueliang Huang Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method
description	As a pivotal technological foundation for smart home implementation, non-intrusive load monitoring is emerging as a widely recognized and popular technology to replace the sensors or sockets networks for the detailed household appliance monitoring. In this paper, a probability model framed ensemble method is proposed for the target of robust appliance monitoring. Firstly, the non-intrusive load disaggregation-oriented ensemble architecture is presented. Then, dictionary learning model is utilized to formulate the individual classifier, while the sparse coding-based approach is capable of providing multiple solutions under greedy mechanism. Furthermore, a fully probabilistic model is established for combined classifier, where the candidate solutions are all labelled with probability scores and evaluated via two-stage decision-making. The proposed method is tested on both low-voltage network simulator platform and field measurement datasets, and the results show that the proposed ensemble method always guarantees an enhancement on the performance of non-intrusive load disaggregation. Besides, the proposed approach shows high flexibility and scalability in classification model selection. Therefore, by initializing the architecture and approach of ensemble method-based NILM, this work plays a pioneer role in using ensemble method to improve the robustness and reliability of non-intrusive appliance monitoring.
format	article
author	Yu Liu Yan Wang Yu Hong Qianyun Shi Shan Gao Xueliang Huang
author_facet	Yu Liu Yan Wang Yu Hong Qianyun Shi Shan Gao Xueliang Huang
author_sort	Yu Liu
title	Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method
title_short	Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method
title_full	Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method
title_fullStr	Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method
title_full_unstemmed	Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method
title_sort	toward robust non-intrusive load monitoring via probability model framed ensemble method
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/02cf742d438c4c388305f9120634ca31
work_keys_str_mv	AT yuliu towardrobustnonintrusiveloadmonitoringviaprobabilitymodelframedensemblemethod AT yanwang towardrobustnonintrusiveloadmonitoringviaprobabilitymodelframedensemblemethod AT yuhong towardrobustnonintrusiveloadmonitoringviaprobabilitymodelframedensemblemethod AT qianyunshi towardrobustnonintrusiveloadmonitoringviaprobabilitymodelframedensemblemethod AT shangao towardrobustnonintrusiveloadmonitoringviaprobabilitymodelframedensemblemethod AT xuelianghuang towardrobustnonintrusiveloadmonitoringviaprobabilitymodelframedensemblemethod
_version_	1718431566158364672

Toward Robust Non-Intrusive Load Monitoring via Probability Model Framed Ensemble Method

Ejemplares similares