NTL Detection of Electricity Theft and Abnormalities for ...people.idsia.ch/~nagi/conferences/scored_ntl_detection.pdf · NTL Detection of Electricity Theft and Abnormalities for
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
NTL Detection of Electricity Theft and Abnormalities
for Large Power Consumers In TNB Malaysia
J. Nagi1,*
K.S. Yap2, F. Nagi
3
1Research Management Centre
UNITEN R&D Sdn. Bhd. University Tenaga Nasional, 43000 Kajang, Malaysia
{jawad,yapkeem,farrukh}@uniten.edu.my
S.K. Tiong1, S. P. Koh1, S. K. Ahmed2 2Dept. of Electronics and Communication Engineering
3Department of Mechanical Engineering
University Tenaga Nasional, 43000 Kajang, Malaysia
{siehkiong,johnnykoh,syedkhaleel}@uniten.edu.my
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 an approach towards
detection of Non-technical Losses (NTLs) of Large Power Consumers (LPC) in Tenaga Nasional Berhad (TNB) Malaysia. The main motivation of this study is to assist Tenaga Nasional
Berhad (TNB) Sdn. Bhd. in Malaysia to reduce its NTLs in the LPC distribution sector. Remote meters installed at premises of
LPC customers transmit power consumption data including
remote meter events wirelessly to TNB Metering Services Sdn. Bhd. The remote meter reading (RMR) consumption data for
TNB LPC customers is recorded based on half-hourly intervals. The technique proposed in this paper correlates the half-hourly
RMR consumption data with abnormal meter events. The correlated data provides information regarding consumption
characteristics i.e. load profiles of LPC customers, which helps to expose abnormal consumption behavior that is known to be
highly correlated with NTL activities and electricity theft. Pilot
testing results obtained from TNB Distribution (TNBD) Sdn. Bhd. for onsite inspection of LPC customers in peninsular
Malaysia indicate the proposed NTL detection technique is effective with a 55% detection hitrate. With the implementation of this intelligent system, NTL activities of LPC customers in
TNB Malaysia will reduce significantly. Keywords—Nontechnical loss, Electricity theft; Fuzzy logic;
Remote meters; Intelligent systems.
I. INTRODUCTION
OWER utilities lose large amounts of money each year
due to fraud by electricity consumers. Electricity fraud
can be defined as a dishonest or illegal use of electricity
equipment or service with the intention to avoid billing
charge. It is relatively difficult to distinguish between honest
and fraudulent customers. Realistically, electric utilities will
never be able to eliminate fraud, however, it is possible to take
measures to detect, prevent and reduce fraud [1].
Distribution losses in power utilities originating from
electricity theft and other customer malfeasances are termed as
Non-technical Losses (NTLs) [1]. Such losses mainly occur
due to meter tampering, meter malfunction, illegal connections
and billing irregularities [2].The problem of NTLs is not only
faced by the least developed countries in the Asian and African
regions, but also by developed countries such as the United
States of America and the United Kingdom. Specifically, high
rates of NTL activities have been reported in the majority of
developing countries in the Association of South East Asian
Nations (ASEAN) group, which include Malaysia, Indonesia,
Thailand, Myanmar and Vietnam [1]. As an example, in
developing countries such as Bangladesh, India, Pakistan and
Lebanon, an average between 20% to 30% of NTLs have been
observed [3], [4].
Investigations are undertaken by electric utility companies
to assess the impact of technical losses in generation,
transmission and distribution networks, and the overall performance of power networks [5], [6]. NTLs comprise one
of the most important concerns for electricity distribution
utilities worldwide. In 2004, Tenaga Nasional Berhad (TNB)
Sdn. Bhd. the sole electricity provider in Malaysia recorded
revenue losses as high as USD 229 million a year as a result of
electricity theft, billing errors and faulty metering [7].
In recent years, several data mining and research studies on
fraud identification and prediction techniques have been carried
out in the electricity distribution sector [8]. These include
Statistical Methods [9-10], Decision Trees [11], Artificial
Neural Networks (ANNs) [12], Knowledge Discovery in
Databases (KDD) [13], and Multiple Classifiers using cross
identification and voting scheme [14]. Among these, load
profiling is one of the most widely used [15], which is defined
as the pattern of electricity consumption of a customer [8].
NTLs for Large Power Consumers (LPCs) appear to have
never been adequately studied, and to date there is no published
evidence of research on detection of NTLs in the LPC
distribution sector of the electricity supply industry. In [3], [7]–
[9], we proposed a NTL detection model using Support Vector
Machines (SVMs) and the Fuzzy Inference System (FIS) for
detection of NTLs in the Ordinary Power Consumer (OPC)
distribution sector of TNB Malaysia. Currently TNB Malaysia is focusing on reducing its NTLs,
in the LPC distribution sector. At present, customer installation
inspections are carried out without any specific focus due to the
remote meter reading (RMR) generating a large number of
event logs for LPC customers. The huge amount of meter event
logs causes confusion in detecting and shortlisting possible
suspects from the RMR data. The approach proposed in this
paper models an intelligent system for assisting TNBD Strike
P
This project is supported by Tenaga Nasional Berhad (TNB) Research in
collaboration with UNITEN R&D Sdn. Bhd. of University Tenaga Nasional, Malaysia.
Proceedings of 2010 IEEE Student Conference on Research and Development (SCOReD 2010), 13 - 14 Dec 2010, Putrajaya, Malaysia