Publication:
Nontechnical loss detection for metered customers in power utility using support vector machines

Simple item page
dc.citedby342
dc.contributor.authorNagi J.en_US
dc.contributor.authorYap K.S.en_US
dc.contributor.authorTiong S.K.en_US
dc.contributor.authorAhmed S.K.en_US
dc.contributor.authorMohamad M.en_US
dc.contributor.authorid25825455100en_US
dc.contributor.authorid24448864400en_US
dc.contributor.authorid15128307800en_US
dc.contributor.authorid25926812900en_US
dc.contributor.authorid24448533500en_US
dc.date.accessioned2023-12-29T07:51:55Z
dc.date.available2023-12-29T07:51:55Z
dc.date.issued2010
dc.description.abstractElectricity 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 nontechnical loss (NTL) detection in power utilities using an artificial intelligence based technique, support vector machine (SVM). The main motivation of this study is to assist Tenaga Nasional Berhad (TNB) Sdn. Bhd. in peninsular Malaysia to reduce its NTLs in the distribution sector due to abnormalities and fraud activities, i.e., electricity theft. The fraud detection model (FDM) developed in this research study preselects suspected customers to be inspected onsite fraud based on irregularities in consumption behavior. This approach provides a method of data mining, which involves feature extraction from historical customer consumption data. This SVM based approach uses customer load profile information and additional attributes to expose abnormal behavior that is known to be highly correlated with NTL activities. The result yields customer classes which are used to shortlist potential suspects for onsite inspection based on significant behavior that emerges due to fraud activities. Model testing is performed using historical kWh consumption data for three towns within peninsular Malaysia. Feedback from TNB Distribution (TNBD) Sdn. Bhd. for onsite inspection indicates that the proposed method is more effective compared to the current actions taken by them. With the implementation of this new fraud detection system TNBD's detection hitrate will increase from 3% to 60%. � 2010 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo5286297
dc.identifier.doi10.1109/TPWRD.2009.2030890
dc.identifier.epage1171
dc.identifier.issue2
dc.identifier.scopus2-s2.0-77950188492
dc.identifier.spage1162
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-77950188492&doi=10.1109%2fTPWRD.2009.2030890&partnerID=40&md5=70a42c7ec2f63999ad88f40a06ef15d0
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/30722
dc.identifier.volume25
dc.pagecount9
dc.sourceScopus
dc.sourcetitleIEEE Transactions on Power Delivery
dc.subjectElectricity theft
dc.subjectIntelligent system
dc.subjectLoad profiling
dc.subjectNontechnical loss
dc.subjectPattern classification
dc.subjectCustomer satisfaction
dc.subjectElectric load forecasting
dc.subjectFeature extraction
dc.subjectGears
dc.subjectInspection
dc.subjectIntelligent systems
dc.subjectMultilayer neural networks
dc.subjectSales
dc.subjectSupport vector machines
dc.subjectAbnormal behavior
dc.subjectCustomer consumption data
dc.subjectCustomer load profiles
dc.subjectDistribution sector
dc.subjectElectricity consumers
dc.subjectElectricity theft
dc.subjectElectricity-consumption
dc.subjectFraud detection
dc.subjectFraud detection system
dc.subjectHighly-correlated
dc.subjectMalaysia
dc.subjectModel testing
dc.subjectNew approaches
dc.subjectNon-technical loss
dc.subjectOn-site inspection
dc.subjectPattern classification
dc.subjectPower utility
dc.subjectResearch areas
dc.subjectResearch studies
dc.subjectCrime
dc.titleNontechnical loss detection for metered customers in power utility using support vector machinesen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS