Home > Research > Publications & Outputs > A Stacked Machine and Deep Learning-based Appro...

Electronic data

  • Inamullah et.al

    Rights statement: ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 2.32 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

A Stacked Machine and Deep Learning-based Approach for Analysing Electricity Theft in Smart Grids

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

A Stacked Machine and Deep Learning-based Approach for Analysing Electricity Theft in Smart Grids. / Khan, Inam Ullah; Javeid, Nadeem; Taylor, C. James et al.
In: IEEE Transactions on Smart Grid, Vol. 13, No. 2, 01.03.2022, p. 1633-1644.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Khan IU, Javeid N, Taylor CJ, Gamage K, Ma X. A Stacked Machine and Deep Learning-based Approach for Analysing Electricity Theft in Smart Grids. IEEE Transactions on Smart Grid. 2022 Mar 1;13(2):1633-1644. Epub 2021 Dec 9. doi: 10.1109/TSG.2021.3134018

Author

Khan, Inam Ullah ; Javeid, Nadeem ; Taylor, C. James et al. / A Stacked Machine and Deep Learning-based Approach for Analysing Electricity Theft in Smart Grids. In: IEEE Transactions on Smart Grid. 2022 ; Vol. 13, No. 2. pp. 1633-1644.

Bibtex

@article{20391064d12340bab29c63cd587fb00c,
title = "A Stacked Machine and Deep Learning-based Approach for Analysing Electricity Theft in Smart Grids",
abstract = "The role of electricity theft detection (ETD) is critical to maintain cost-efficiency in smart grids. However, existing methods for theft detection can struggle to handle large electricity consumption datasets because of missing values, data variance and nonlinear data relationship problems, and there is a lack of integrated infrastructure for coordinating electricity load data analysis procedures. To help address these problems, a simple yet effective ETD model is developed. Three modules are combined into the proposed model. The first module deploys a combination of data imputation, outlier handling, normalization and class balancing algorithms, to enhance the time series characteristics and generate better quality data for improved training and learning by the classifiers. Three different machine learning (ML) methods, which are uncorrelated and skillful on the problem in different ways, are employed as the base learning model. Finally, a recently developed deep learning approach, namely a temporal convolutional network (TCN), is used to ensemble the outputs of the ML algorithms for improved classification accuracy. Experimental results confirm that the proposed framework yields a highly-accurate, robust classification performance, in comparison to other well-established machine and deep learning models and thus can be a practical tool for electricity theft detection in industrial applications.",
author = "Khan, {Inam Ullah} and Nadeem Javeid and Taylor, {C. James} and Kelum Gamage and Xiandong Ma",
note = "{\textcopyright}2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. ",
year = "2022",
month = mar,
day = "1",
doi = "10.1109/TSG.2021.3134018",
language = "English",
volume = "13",
pages = "1633--1644",
journal = "IEEE Transactions on Smart Grid",
issn = "1949-3053",
publisher = "IEEE",
number = "2",

}

RIS

TY - JOUR

T1 - A Stacked Machine and Deep Learning-based Approach for Analysing Electricity Theft in Smart Grids

AU - Khan, Inam Ullah

AU - Javeid, Nadeem

AU - Taylor, C. James

AU - Gamage, Kelum

AU - Ma, Xiandong

N1 - ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2022/3/1

Y1 - 2022/3/1

N2 - The role of electricity theft detection (ETD) is critical to maintain cost-efficiency in smart grids. However, existing methods for theft detection can struggle to handle large electricity consumption datasets because of missing values, data variance and nonlinear data relationship problems, and there is a lack of integrated infrastructure for coordinating electricity load data analysis procedures. To help address these problems, a simple yet effective ETD model is developed. Three modules are combined into the proposed model. The first module deploys a combination of data imputation, outlier handling, normalization and class balancing algorithms, to enhance the time series characteristics and generate better quality data for improved training and learning by the classifiers. Three different machine learning (ML) methods, which are uncorrelated and skillful on the problem in different ways, are employed as the base learning model. Finally, a recently developed deep learning approach, namely a temporal convolutional network (TCN), is used to ensemble the outputs of the ML algorithms for improved classification accuracy. Experimental results confirm that the proposed framework yields a highly-accurate, robust classification performance, in comparison to other well-established machine and deep learning models and thus can be a practical tool for electricity theft detection in industrial applications.

AB - The role of electricity theft detection (ETD) is critical to maintain cost-efficiency in smart grids. However, existing methods for theft detection can struggle to handle large electricity consumption datasets because of missing values, data variance and nonlinear data relationship problems, and there is a lack of integrated infrastructure for coordinating electricity load data analysis procedures. To help address these problems, a simple yet effective ETD model is developed. Three modules are combined into the proposed model. The first module deploys a combination of data imputation, outlier handling, normalization and class balancing algorithms, to enhance the time series characteristics and generate better quality data for improved training and learning by the classifiers. Three different machine learning (ML) methods, which are uncorrelated and skillful on the problem in different ways, are employed as the base learning model. Finally, a recently developed deep learning approach, namely a temporal convolutional network (TCN), is used to ensemble the outputs of the ML algorithms for improved classification accuracy. Experimental results confirm that the proposed framework yields a highly-accurate, robust classification performance, in comparison to other well-established machine and deep learning models and thus can be a practical tool for electricity theft detection in industrial applications.

U2 - 10.1109/TSG.2021.3134018

DO - 10.1109/TSG.2021.3134018

M3 - Journal article

VL - 13

SP - 1633

EP - 1644

JO - IEEE Transactions on Smart Grid

JF - IEEE Transactions on Smart Grid

SN - 1949-3053

IS - 2

ER -