Detection of abnormalities and electricity theft using genetic support vector machines

Research output: Chapter in Book/Report/Conference proceedingConference contribution

87 Citations (Scopus)

Abstract

Efficient methods for detecting electricity fraud has been an active research area in recent years. This paper presents a hybrid approach towards Non-Technical Loss (NTL) analysis for electric utilities using Genetic Algorithm (GA) and Support Vector Machine (SVM). The main motivation of this study is to assist Tenaga Nasional Berhad (TNB) in Malaysia to reduce its NTLs in the distribution sector. This hybrid GA-SVM model preselects suspected customers to be inspected onsite for fraud based on abnormal consumption behavior. The proposed approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. GA provides an increased convergence and globally optimized SVM hyper-parameters using a combination of random and prepopulated genomes. The result of the fraud detection model yields classified classes that are used to shortlist potential fraud suspects for onsite inspection. Simulation results prove the proposed method is more effective compared to the current actions taken by TNB in order to reduce NTL activities.

Original languageEnglish
Title of host publication2008 IEEE Region 10 Conference, TENCON 2008
DOIs
Publication statusPublished - 01 Dec 2008
Event2008 IEEE Region 10 Conference, TENCON 2008 - Hyderabad, India
Duration: 19 Nov 200821 Nov 2008

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON

Other

Other2008 IEEE Region 10 Conference, TENCON 2008
CountryIndia
CityHyderabad
Period19/11/0821/11/08

Fingerprint

Support vector machines
Electricity
Genetic algorithms
Electric utilities
Genes
Inspection

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Nagi, J., Yap, K. S., Tiong, S. K., Khaleel Ahmed, S., & Mohammad, A. M. (2008). Detection of abnormalities and electricity theft using genetic support vector machines. In 2008 IEEE Region 10 Conference, TENCON 2008 [4766403] (IEEE Region 10 Annual International Conference, Proceedings/TENCON). https://doi.org/10.1109/TENCON.2008.4766403
Nagi, J. ; Yap, Keem Siah ; Tiong, Sieh Kiong ; Khaleel Ahmed, Syed ; Mohammad, A. M. / Detection of abnormalities and electricity theft using genetic support vector machines. 2008 IEEE Region 10 Conference, TENCON 2008. 2008. (IEEE Region 10 Annual International Conference, Proceedings/TENCON).
@inproceedings{2d62ab47c7a34d30857e04243a4e65ae,
title = "Detection of abnormalities and electricity theft using genetic support vector machines",
abstract = "Efficient methods for detecting electricity fraud has been an active research area in recent years. This paper presents a hybrid approach towards Non-Technical Loss (NTL) analysis for electric utilities using Genetic Algorithm (GA) and Support Vector Machine (SVM). The main motivation of this study is to assist Tenaga Nasional Berhad (TNB) in Malaysia to reduce its NTLs in the distribution sector. This hybrid GA-SVM model preselects suspected customers to be inspected onsite for fraud based on abnormal consumption behavior. The proposed approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. GA provides an increased convergence and globally optimized SVM hyper-parameters using a combination of random and prepopulated genomes. The result of the fraud detection model yields classified classes that are used to shortlist potential fraud suspects for onsite inspection. Simulation results prove the proposed method is more effective compared to the current actions taken by TNB in order to reduce NTL activities.",
author = "J. Nagi and Yap, {Keem Siah} and Tiong, {Sieh Kiong} and {Khaleel Ahmed}, Syed and Mohammad, {A. M.}",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/TENCON.2008.4766403",
language = "English",
isbn = "1424424089",
series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",
booktitle = "2008 IEEE Region 10 Conference, TENCON 2008",

}

Nagi, J, Yap, KS, Tiong, SK, Khaleel Ahmed, S & Mohammad, AM 2008, Detection of abnormalities and electricity theft using genetic support vector machines. in 2008 IEEE Region 10 Conference, TENCON 2008., 4766403, IEEE Region 10 Annual International Conference, Proceedings/TENCON, 2008 IEEE Region 10 Conference, TENCON 2008, Hyderabad, India, 19/11/08. https://doi.org/10.1109/TENCON.2008.4766403

Detection of abnormalities and electricity theft using genetic support vector machines. / Nagi, J.; Yap, Keem Siah; Tiong, Sieh Kiong; Khaleel Ahmed, Syed; Mohammad, A. M.

2008 IEEE Region 10 Conference, TENCON 2008. 2008. 4766403 (IEEE Region 10 Annual International Conference, Proceedings/TENCON).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Detection of abnormalities and electricity theft using genetic support vector machines

AU - Nagi, J.

AU - Yap, Keem Siah

AU - Tiong, Sieh Kiong

AU - Khaleel Ahmed, Syed

AU - Mohammad, A. M.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Efficient methods for detecting electricity fraud has been an active research area in recent years. This paper presents a hybrid approach towards Non-Technical Loss (NTL) analysis for electric utilities using Genetic Algorithm (GA) and Support Vector Machine (SVM). The main motivation of this study is to assist Tenaga Nasional Berhad (TNB) in Malaysia to reduce its NTLs in the distribution sector. This hybrid GA-SVM model preselects suspected customers to be inspected onsite for fraud based on abnormal consumption behavior. The proposed approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. GA provides an increased convergence and globally optimized SVM hyper-parameters using a combination of random and prepopulated genomes. The result of the fraud detection model yields classified classes that are used to shortlist potential fraud suspects for onsite inspection. Simulation results prove the proposed method is more effective compared to the current actions taken by TNB in order to reduce NTL activities.

AB - Efficient methods for detecting electricity fraud has been an active research area in recent years. This paper presents a hybrid approach towards Non-Technical Loss (NTL) analysis for electric utilities using Genetic Algorithm (GA) and Support Vector Machine (SVM). The main motivation of this study is to assist Tenaga Nasional Berhad (TNB) in Malaysia to reduce its NTLs in the distribution sector. This hybrid GA-SVM model preselects suspected customers to be inspected onsite for fraud based on abnormal consumption behavior. The proposed approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. GA provides an increased convergence and globally optimized SVM hyper-parameters using a combination of random and prepopulated genomes. The result of the fraud detection model yields classified classes that are used to shortlist potential fraud suspects for onsite inspection. Simulation results prove the proposed method is more effective compared to the current actions taken by TNB in order to reduce NTL activities.

UR - http://www.scopus.com/inward/record.url?scp=63049100877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63049100877&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2008.4766403

DO - 10.1109/TENCON.2008.4766403

M3 - Conference contribution

SN - 1424424089

SN - 9781424424085

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

BT - 2008 IEEE Region 10 Conference, TENCON 2008

ER -

Nagi J, Yap KS, Tiong SK, Khaleel Ahmed S, Mohammad AM. Detection of abnormalities and electricity theft using genetic support vector machines. In 2008 IEEE Region 10 Conference, TENCON 2008. 2008. 4766403. (IEEE Region 10 Annual International Conference, Proceedings/TENCON). https://doi.org/10.1109/TENCON.2008.4766403