Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network

Electricity theft behavior has serious influence on the normal operation of power grid and the economic benefits of power enterprises. Intelligent anti-power-theft algorithm is required for monitoring the power consumption data to recognize electricity power theft. In this paper, an adaptive time-se...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Guoying Lin, Haoyang Feng, Xiaofeng Feng, Hongwu Wen, Yuanzheng Li, Shaoyong Hong, Zhixian Ni
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	electricity theft TSRNN adaptive parameter tuning intelligent learning SMOTE power consumption data General Works A
Acceso en línea:	https://doaj.org/article/6f40460e4bc044d491031deef40044ba
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6f40460e4bc044d491031deef40044ba
record_format	dspace
spelling	oai:doaj.org-article:6f40460e4bc044d491031deef40044ba2021-11-10T07:21:29ZElectricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network2296-598X10.3389/fenrg.2021.773805https://doaj.org/article/6f40460e4bc044d491031deef40044ba2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fenrg.2021.773805/fullhttps://doaj.org/toc/2296-598XElectricity theft behavior has serious influence on the normal operation of power grid and the economic benefits of power enterprises. Intelligent anti-power-theft algorithm is required for monitoring the power consumption data to recognize electricity power theft. In this paper, an adaptive time-series recurrent neural network (TSRNN) architecture was built up to detect the abnormal users (i.e., the electricity theft users) in time-series data of the power consumption. In fusion with the synthetic minority oversampling technique (SMOTE) algorithm, a batch of virtual abnormal observations were generated as the implementation for training the TSRNN model. The power consumption record was characterized with the sharp data (ARP), the peak data (PEA), and the shoulder data (SHO). In the TSRNN architectural framework, a basic network unit was formed with three input nodes linked to one hidden neuron for extracting data features from the three characteristic variables. For time-series analysis, the TSRNN structure was re-formed by circulating the basic unit. Each hidden node was designed receiving data from both the current input neurons and the time-former neuron, thus to form a combination of network linking weights for adaptive tuning. The optimization of the TSRNN model is to automatically search for the most suitable values of these linking weights driven by the collected and simulated data. The TSRNN model was trained and optimized with a high discriminant accuracy of 95.1%, and evaluated to have 89.3% accuracy. Finally, the optimized TSRNN model was used to predict the 47 real abnormal samples, resulting in having only three samples false predicted. These experimental results indicated that the proposed adaptive TSRNN architecture combined with SMOTE is feasible to identify the abnormal electricity theft behavior. It is prospective to be applied to online monitoring of distributed analysis of large-scale electricity power consumption data.Guoying LinGuoying LinHaoyang FengXiaofeng FengHongwu WenYuanzheng LiShaoyong HongZhixian NiFrontiers Media S.A.articleelectricity theftTSRNNadaptive parameter tuningintelligent learningSMOTEpower consumption dataGeneral WorksAENFrontiers in Energy Research, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	electricity theft TSRNN adaptive parameter tuning intelligent learning SMOTE power consumption data General Works A
spellingShingle	electricity theft TSRNN adaptive parameter tuning intelligent learning SMOTE power consumption data General Works A Guoying Lin Guoying Lin Haoyang Feng Xiaofeng Feng Hongwu Wen Yuanzheng Li Shaoyong Hong Zhixian Ni Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network
description	Electricity theft behavior has serious influence on the normal operation of power grid and the economic benefits of power enterprises. Intelligent anti-power-theft algorithm is required for monitoring the power consumption data to recognize electricity power theft. In this paper, an adaptive time-series recurrent neural network (TSRNN) architecture was built up to detect the abnormal users (i.e., the electricity theft users) in time-series data of the power consumption. In fusion with the synthetic minority oversampling technique (SMOTE) algorithm, a batch of virtual abnormal observations were generated as the implementation for training the TSRNN model. The power consumption record was characterized with the sharp data (ARP), the peak data (PEA), and the shoulder data (SHO). In the TSRNN architectural framework, a basic network unit was formed with three input nodes linked to one hidden neuron for extracting data features from the three characteristic variables. For time-series analysis, the TSRNN structure was re-formed by circulating the basic unit. Each hidden node was designed receiving data from both the current input neurons and the time-former neuron, thus to form a combination of network linking weights for adaptive tuning. The optimization of the TSRNN model is to automatically search for the most suitable values of these linking weights driven by the collected and simulated data. The TSRNN model was trained and optimized with a high discriminant accuracy of 95.1%, and evaluated to have 89.3% accuracy. Finally, the optimized TSRNN model was used to predict the 47 real abnormal samples, resulting in having only three samples false predicted. These experimental results indicated that the proposed adaptive TSRNN architecture combined with SMOTE is feasible to identify the abnormal electricity theft behavior. It is prospective to be applied to online monitoring of distributed analysis of large-scale electricity power consumption data.
format	article
author	Guoying Lin Guoying Lin Haoyang Feng Xiaofeng Feng Hongwu Wen Yuanzheng Li Shaoyong Hong Zhixian Ni
author_facet	Guoying Lin Guoying Lin Haoyang Feng Xiaofeng Feng Hongwu Wen Yuanzheng Li Shaoyong Hong Zhixian Ni
author_sort	Guoying Lin
title	Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network
title_short	Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network
title_full	Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network
title_fullStr	Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network
title_full_unstemmed	Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network
title_sort	electricity theft detection in power consumption data based on adaptive tuning recurrent neural network
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/6f40460e4bc044d491031deef40044ba
work_keys_str_mv	AT guoyinglin electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork AT guoyinglin electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork AT haoyangfeng electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork AT xiaofengfeng electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork AT hongwuwen electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork AT yuanzhengli electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork AT shaoyonghong electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork AT zhixianni electricitytheftdetectioninpowerconsumptiondatabasedonadaptivetuningrecurrentneuralnetwork
_version_	1718440477663952896

Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network

Ejemplares similares