A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids

Electricity theft has significant impact on the power grids in terms of generating non-technical losses, which eventually degrading the power quality and minimizing the outfitted profit. In this paper, we proposed a hybrid approach based on deep learning and support vector machine for the detection...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ejaz Ul Haq, Jianjun Huang, Huarong Xu, Kang Li, Fiaz Ahmad
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Electricity theft Non-technical losses Smart meter Convolutional neural networks Support vector machine Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/fb32710845b8496b80ab0d9e18ecf094
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fb32710845b8496b80ab0d9e18ecf094
record_format	dspace
spelling	oai:doaj.org-article:fb32710845b8496b80ab0d9e18ecf0942021-11-26T04:32:58ZA hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids2352-484710.1016/j.egyr.2021.08.038https://doaj.org/article/fb32710845b8496b80ab0d9e18ecf0942021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2352484721006405https://doaj.org/toc/2352-4847Electricity theft has significant impact on the power grids in terms of generating non-technical losses, which eventually degrading the power quality and minimizing the outfitted profit. In this paper, we proposed a hybrid approach based on deep learning and support vector machine for the detection of energy theft to facilitate and assess energy supplier companies to eliminate the issue of insufficient power, irregular power expenditure and ineffective electricity monitoring. A deep convolutional neural network is proposed for the feature learning using smart meters data in different times, varying from hours to days. Extracted features were further used to train support vector machine, which classify the features in two categories as theft and non-theft. Furthermore, a dropout layer is introduced in convolutional neural network model to avoid over fitting issues. Several careful experiments were carried out on real time customers smart meter data and the results validate the effectiveness of the proposed method in terms of accuracy and less detection error.Ejaz Ul HaqJianjun HuangHuarong XuKang LiFiaz AhmadElsevierarticleElectricity theftNon-technical lossesSmart meterConvolutional neural networksSupport vector machineElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENEnergy Reports, Vol 7, Iss , Pp 349-356 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electricity theft Non-technical losses Smart meter Convolutional neural networks Support vector machine Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Electricity theft Non-technical losses Smart meter Convolutional neural networks Support vector machine Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ejaz Ul Haq Jianjun Huang Huarong Xu Kang Li Fiaz Ahmad A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids
description	Electricity theft has significant impact on the power grids in terms of generating non-technical losses, which eventually degrading the power quality and minimizing the outfitted profit. In this paper, we proposed a hybrid approach based on deep learning and support vector machine for the detection of energy theft to facilitate and assess energy supplier companies to eliminate the issue of insufficient power, irregular power expenditure and ineffective electricity monitoring. A deep convolutional neural network is proposed for the feature learning using smart meters data in different times, varying from hours to days. Extracted features were further used to train support vector machine, which classify the features in two categories as theft and non-theft. Furthermore, a dropout layer is introduced in convolutional neural network model to avoid over fitting issues. Several careful experiments were carried out on real time customers smart meter data and the results validate the effectiveness of the proposed method in terms of accuracy and less detection error.
format	article
author	Ejaz Ul Haq Jianjun Huang Huarong Xu Kang Li Fiaz Ahmad
author_facet	Ejaz Ul Haq Jianjun Huang Huarong Xu Kang Li Fiaz Ahmad
author_sort	Ejaz Ul Haq
title	A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids
title_short	A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids
title_full	A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids
title_fullStr	A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids
title_full_unstemmed	A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids
title_sort	hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/fb32710845b8496b80ab0d9e18ecf094
work_keys_str_mv	AT ejazulhaq ahybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT jianjunhuang ahybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT huarongxu ahybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT kangli ahybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT fiazahmad ahybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT ejazulhaq hybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT jianjunhuang hybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT huarongxu hybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT kangli hybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids AT fiazahmad hybridapproachbasedondeeplearningandsupportvectormachineforthedetectionofelectricitytheftinpowergrids
_version_	1718409878857318400

A hybrid approach based on deep learning and support vector machine for the detection of electricity theft in power grids

Ejemplares similares