Comparison of supervised learning techniques for non-technical loss detection in power utility

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Non technical losses (NTLs) originating from electricity theft and other customer malfeasances are a problem in the electricity supply industry. In recent times, electricity consumer dishonesty has become a universal problem faced by all power utilities. Previous work carried out for NTL detection resulted in a Support Vector Machine (SVM) based detection framework. The present study performs a comparative study for NTL detection using supervised machine learning techniques such as the: Back-Propagation Neural Network (BPNN) and Online-sequential Extreme Learning Machine (OS-ELM). Model testing is performed using historical customer consumption data for three towns within peninsular Malaysia. The detection hit-rate of all compared models is obtained from TNB Distribution (TNBD) Sdn. Bhd. for onsite customer inspection. Experimental results obtained indicate that the BPNN detection model achieves the lowest average detection hit-rate of 36.07%, while the OS-ELM model obtains a slightly higher average detection hit-rate of 51.38%. The previously proposed SVM-based NTL detection model outperforms the BPNN and OS-ELM by far with the highest average detection hit-rate of 60.75%. This indicates that the use of a SVM-based soft-margin approach results in a better generalization performance for the application of NTL detection as compared to the BPNN and OS-ELM schemes.

Original languageEnglish
Pages (from-to)626-636
Number of pages11
JournalInternational Review on Computers and Software
Volume7
Issue number2
Publication statusPublished - 01 Aug 2012

Fingerprint

Supervised learning
Learning systems
Backpropagation
Neural networks
Support vector machines
Electricity
Electric utilities
Inspection
Testing

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

@article{f5c1232587c64d6da8185d9bde8e8ac2,
title = "Comparison of supervised learning techniques for non-technical loss detection in power utility",
abstract = "Non technical losses (NTLs) originating from electricity theft and other customer malfeasances are a problem in the electricity supply industry. In recent times, electricity consumer dishonesty has become a universal problem faced by all power utilities. Previous work carried out for NTL detection resulted in a Support Vector Machine (SVM) based detection framework. The present study performs a comparative study for NTL detection using supervised machine learning techniques such as the: Back-Propagation Neural Network (BPNN) and Online-sequential Extreme Learning Machine (OS-ELM). Model testing is performed using historical customer consumption data for three towns within peninsular Malaysia. The detection hit-rate of all compared models is obtained from TNB Distribution (TNBD) Sdn. Bhd. for onsite customer inspection. Experimental results obtained indicate that the BPNN detection model achieves the lowest average detection hit-rate of 36.07{\%}, while the OS-ELM model obtains a slightly higher average detection hit-rate of 51.38{\%}. The previously proposed SVM-based NTL detection model outperforms the BPNN and OS-ELM by far with the highest average detection hit-rate of 60.75{\%}. This indicates that the use of a SVM-based soft-margin approach results in a better generalization performance for the application of NTL detection as compared to the BPNN and OS-ELM schemes.",
author = "Yap, {Keem Siah} and Tiong, {Sieh Kiong} and Jawad Nagi and Koh, {Johnny Siaw Paw} and Farrukh Nagi",
year = "2012",
month = "8",
day = "1",
language = "English",
volume = "7",
pages = "626--636",
journal = "International Review on Computers and Software",
issn = "1828-6003",
publisher = "Praise Worthy Prize",
number = "2",

}

TY - JOUR

T1 - Comparison of supervised learning techniques for non-technical loss detection in power utility

AU - Yap, Keem Siah

AU - Tiong, Sieh Kiong

AU - Nagi, Jawad

AU - Koh, Johnny Siaw Paw

AU - Nagi, Farrukh

PY - 2012/8/1

Y1 - 2012/8/1

N2 - Non technical losses (NTLs) originating from electricity theft and other customer malfeasances are a problem in the electricity supply industry. In recent times, electricity consumer dishonesty has become a universal problem faced by all power utilities. Previous work carried out for NTL detection resulted in a Support Vector Machine (SVM) based detection framework. The present study performs a comparative study for NTL detection using supervised machine learning techniques such as the: Back-Propagation Neural Network (BPNN) and Online-sequential Extreme Learning Machine (OS-ELM). Model testing is performed using historical customer consumption data for three towns within peninsular Malaysia. The detection hit-rate of all compared models is obtained from TNB Distribution (TNBD) Sdn. Bhd. for onsite customer inspection. Experimental results obtained indicate that the BPNN detection model achieves the lowest average detection hit-rate of 36.07%, while the OS-ELM model obtains a slightly higher average detection hit-rate of 51.38%. The previously proposed SVM-based NTL detection model outperforms the BPNN and OS-ELM by far with the highest average detection hit-rate of 60.75%. This indicates that the use of a SVM-based soft-margin approach results in a better generalization performance for the application of NTL detection as compared to the BPNN and OS-ELM schemes.

AB - Non technical losses (NTLs) originating from electricity theft and other customer malfeasances are a problem in the electricity supply industry. In recent times, electricity consumer dishonesty has become a universal problem faced by all power utilities. Previous work carried out for NTL detection resulted in a Support Vector Machine (SVM) based detection framework. The present study performs a comparative study for NTL detection using supervised machine learning techniques such as the: Back-Propagation Neural Network (BPNN) and Online-sequential Extreme Learning Machine (OS-ELM). Model testing is performed using historical customer consumption data for three towns within peninsular Malaysia. The detection hit-rate of all compared models is obtained from TNB Distribution (TNBD) Sdn. Bhd. for onsite customer inspection. Experimental results obtained indicate that the BPNN detection model achieves the lowest average detection hit-rate of 36.07%, while the OS-ELM model obtains a slightly higher average detection hit-rate of 51.38%. The previously proposed SVM-based NTL detection model outperforms the BPNN and OS-ELM by far with the highest average detection hit-rate of 60.75%. This indicates that the use of a SVM-based soft-margin approach results in a better generalization performance for the application of NTL detection as compared to the BPNN and OS-ELM schemes.

UR - http://www.scopus.com/inward/record.url?scp=84864352618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864352618&partnerID=8YFLogxK

M3 - Article

VL - 7

SP - 626

EP - 636

JO - International Review on Computers and Software

JF - International Review on Computers and Software

SN - 1828-6003

IS - 2

ER -