Towards Efficient Energy Utilization Using Big Data Analytics in Smart Cities for Electricity Theft Detection

Arif, A; Alghamdi, TA; Khan, ZA; Javaid, N

Towards Efficient Energy Utilization Using Big Data Analytics in Smart Cities for Electricity Theft Detection

Arif, A Alghamdi, TA Khan, ZA Javaid, N

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Big Data Research, 2022, 27, pp. 100285
Issue Date:: 2022-02-28

Closed Access

	Filename	Description	Size
	1-s2.0-S2214579621001027-main.pdf	Published version	1.89 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Arif, A
dc.contributor.author	Alghamdi, TA
dc.contributor.author	Khan, ZA
dc.contributor.author	Javaid, N
dc.date.accessioned	2023-07-03T02:51:50Z
dc.date.available	2023-07-03T02:51:50Z
dc.date.issued	2022-02-28
dc.identifier.citation	Big Data Research, 2022, 27, pp. 100285
dc.identifier.issn	2214-5796
dc.identifier.issn	2214-5796
dc.identifier.uri	http://hdl.handle.net/10453/171133
dc.description.abstract	In energy sectors, power utilities face financial losses due to Electricity Theft (ET). It happens when electricity is consumed without billing. Several methods are developed to detect ET automatically. Most of these methods only assess Electricity Consumption (EC) records. However, it is challenging to detect fraudulent consumers by only observing EC records because of diverse theft strategies (line tapping, meter tampering, etc.) and the irregularity of ET behavior. Furthermore, many methods have poor classification accuracy due to imbalanced data. This work proposes two novel methods to resolve the above-mentioned issues: Tomek Link Borderline Synthetic Minority Oversampling Technique with Support Vector Machine (TBSSVM) and Temporal Convolutional Network with Enhanced Multi-Layer Perceptron (TCN-EMLP). The former resamples the data by balancing the majority and minority class instances. Whereas, the latter classifies normal and fraudulent consumers. Moreover, deep learning models suffer from high variance in their final results due to the assignment of different weights. Therefore, an averaging ensemble strategy is applied in this work to reduce the high variance. Furthermore, State Grid Cooperation of China (SGCC) and Pakistan Residential Electricity Consumption (PRECON) datasets are used in this paper for performing the simulations. SGCC is an imbalanced and labeled dataset while PRECON is an unlabeled dataset comprised of normal consumers' EC records (sequential) and auxiliary (non-sequential) data. Simulation results show that the proposed model outperforms the baselines, i.e., wide and deep convolutional neural network, extreme gradient boosting, long short-term memory with multi-layer perceptron, etc., in terms of ET detection.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Big Data Research
dc.relation.isbasedon	10.1016/j.bdr.2021.100285
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0104 Statistics, 0801 Artificial Intelligence and Image Processing, 0806 Information Systems
dc.title	Towards Efficient Energy Utilization Using Big Data Analytics in Smart Cities for Electricity Theft Detection
dc.type	Journal Article
utslib.citation.volume	27
utslib.for	0104 Statistics
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
utslib.copyright.status	closed_access	*
dc.date.updated	2023-07-03T02:51:49Z
pubs.publication-status	Published
pubs.volume	27

Abstract:

In energy sectors, power utilities face financial losses due to Electricity Theft (ET). It happens when electricity is consumed without billing. Several methods are developed to detect ET automatically. Most of these methods only assess Electricity Consumption (EC) records. However, it is challenging to detect fraudulent consumers by only observing EC records because of diverse theft strategies (line tapping, meter tampering, etc.) and the irregularity of ET behavior. Furthermore, many methods have poor classification accuracy due to imbalanced data. This work proposes two novel methods to resolve the above-mentioned issues: Tomek Link Borderline Synthetic Minority Oversampling Technique with Support Vector Machine (TBSSVM) and Temporal Convolutional Network with Enhanced Multi-Layer Perceptron (TCN-EMLP). The former resamples the data by balancing the majority and minority class instances. Whereas, the latter classifies normal and fraudulent consumers. Moreover, deep learning models suffer from high variance in their final results due to the assignment of different weights. Therefore, an averaging ensemble strategy is applied in this work to reduce the high variance. Furthermore, State Grid Cooperation of China (SGCC) and Pakistan Residential Electricity Consumption (PRECON) datasets are used in this paper for performing the simulations. SGCC is an imbalanced and labeled dataset while PRECON is an unlabeled dataset comprised of normal consumers' EC records (sequential) and auxiliary (non-sequential) data. Simulation results show that the proposed model outperforms the baselines, i.e., wide and deep convolutional neural network, extreme gradient boosting, long short-term memory with multi-layer perceptron, etc., in terms of ET detection.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/171133