Non-technical loss analysis for detection of electricity theft using support vector machines

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

61 Citations (Scopus)

Abstract

Electricity consumer dishonesty is a problem faced by all power utilities. Finding efficient measurements for detecting fraudulent electricity consumption has been an active research area in recent years. This paper presents a new approach towards Non-Technical Loss (NTL) analysis for electric utilities using a novel intelligence-based technique, 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 due to electricity theft. The proposed model preselects suspected customers to be inspected onsite for fraud based on irregularities and abnormal consumption behavior. This approach provides a method of data mining and involves feature extraction from historical customer consumption data. The SVM based approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. The result yields classification classes that are used to shortlist potential fraud suspects for onsite inspection, based on significant behavior that emerges due to irregularities in consumption. 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 publicationPECon 2008 - 2008 IEEE 2nd International Power and Energy Conference
Pages907-912
Number of pages6
DOIs
Publication statusPublished - 01 Dec 2008
Event2008 IEEE 2nd International Power and Energy Conference, PECon 2008 - Johor Baharu, Malaysia
Duration: 01 Dec 200803 Dec 2008

Publication series

NamePECon 2008 - 2008 IEEE 2nd International Power and Energy Conference

Other

Other2008 IEEE 2nd International Power and Energy Conference, PECon 2008
CountryMalaysia
CityJohor Baharu
Period01/12/0803/12/08

Fingerprint

Support vector machines
Electricity
Electric utilities
Data mining
Feature extraction
Inspection

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

Nagi, J., Mohammad, A. M., Yap, K. S., Tiong, S. K., & Khaleel Ahmed, S. (2008). Non-technical loss analysis for detection of electricity theft using support vector machines. In PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference (pp. 907-912). [4762604] (PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference). https://doi.org/10.1109/PECON.2008.4762604
Nagi, J. ; Mohammad, A. M. ; Yap, Keem Siah ; Tiong, Sieh Kiong ; Khaleel Ahmed, Syed. / Non-technical loss analysis for detection of electricity theft using support vector machines. PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference. 2008. pp. 907-912 (PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference).
@inproceedings{624f087835da40d99865565cbfc86c52,
title = "Non-technical loss analysis for detection of electricity theft using support vector machines",
abstract = "Electricity consumer dishonesty is a problem faced by all power utilities. Finding efficient measurements for detecting fraudulent electricity consumption has been an active research area in recent years. This paper presents a new approach towards Non-Technical Loss (NTL) analysis for electric utilities using a novel intelligence-based technique, 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 due to electricity theft. The proposed model preselects suspected customers to be inspected onsite for fraud based on irregularities and abnormal consumption behavior. This approach provides a method of data mining and involves feature extraction from historical customer consumption data. The SVM based approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. The result yields classification classes that are used to shortlist potential fraud suspects for onsite inspection, based on significant behavior that emerges due to irregularities in consumption. 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 Mohammad, {A. M.} and Yap, {Keem Siah} and Tiong, {Sieh Kiong} and {Khaleel Ahmed}, Syed",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/PECON.2008.4762604",
language = "English",
isbn = "9781424424054",
series = "PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference",
pages = "907--912",
booktitle = "PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference",

}

Nagi, J, Mohammad, AM, Yap, KS, Tiong, SK & Khaleel Ahmed, S 2008, Non-technical loss analysis for detection of electricity theft using support vector machines. in PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference., 4762604, PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference, pp. 907-912, 2008 IEEE 2nd International Power and Energy Conference, PECon 2008, Johor Baharu, Malaysia, 01/12/08. https://doi.org/10.1109/PECON.2008.4762604

Non-technical loss analysis for detection of electricity theft using support vector machines. / Nagi, J.; Mohammad, A. M.; Yap, Keem Siah; Tiong, Sieh Kiong; Khaleel Ahmed, Syed.

PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference. 2008. p. 907-912 4762604 (PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference).

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

TY - GEN

T1 - Non-technical loss analysis for detection of electricity theft using support vector machines

AU - Nagi, J.

AU - Mohammad, A. M.

AU - Yap, Keem Siah

AU - Tiong, Sieh Kiong

AU - Khaleel Ahmed, Syed

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Electricity consumer dishonesty is a problem faced by all power utilities. Finding efficient measurements for detecting fraudulent electricity consumption has been an active research area in recent years. This paper presents a new approach towards Non-Technical Loss (NTL) analysis for electric utilities using a novel intelligence-based technique, 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 due to electricity theft. The proposed model preselects suspected customers to be inspected onsite for fraud based on irregularities and abnormal consumption behavior. This approach provides a method of data mining and involves feature extraction from historical customer consumption data. The SVM based approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. The result yields classification classes that are used to shortlist potential fraud suspects for onsite inspection, based on significant behavior that emerges due to irregularities in consumption. Simulation results prove the proposed method is more effective compared to the current actions taken by TNB in order to reduce NTL activities.

AB - Electricity consumer dishonesty is a problem faced by all power utilities. Finding efficient measurements for detecting fraudulent electricity consumption has been an active research area in recent years. This paper presents a new approach towards Non-Technical Loss (NTL) analysis for electric utilities using a novel intelligence-based technique, 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 due to electricity theft. The proposed model preselects suspected customers to be inspected onsite for fraud based on irregularities and abnormal consumption behavior. This approach provides a method of data mining and involves feature extraction from historical customer consumption data. The SVM based approach uses customer load profile information to expose abnormal behavior that is known to be highly correlated with NTL activities. The result yields classification classes that are used to shortlist potential fraud suspects for onsite inspection, based on significant behavior that emerges due to irregularities in consumption. 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=63049087680&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63049087680&partnerID=8YFLogxK

U2 - 10.1109/PECON.2008.4762604

DO - 10.1109/PECON.2008.4762604

M3 - Conference contribution

SN - 9781424424054

T3 - PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference

SP - 907

EP - 912

BT - PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference

ER -

Nagi J, Mohammad AM, Yap KS, Tiong SK, Khaleel Ahmed S. Non-technical loss analysis for detection of electricity theft using support vector machines. In PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference. 2008. p. 907-912. 4762604. (PECon 2008 - 2008 IEEE 2nd International Power and Energy Conference). https://doi.org/10.1109/PECON.2008.4762604