Scribd
Upload
77 views7 pages

Front Page Ramesh

The document describes a proposed method for electricity theft detection in AMI systems using clustering and local outlier factor analysis. It introduces AMI systems and issues with electricity theft. The proposed method uses k-means clustering to identify outlier candidates, and then applies local outlier factor to calculate anomaly scores and detect theft. The performance of the presented method is evaluated on a realistic dataset.

Uploaded by

Arun K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
77 views7 pages

Front Page Ramesh

The document describes a proposed method for electricity theft detection in AMI systems using clustering and local outlier factor analysis. It introduces AMI systems and issues with electricity theft. The proposed method uses k-means clustering to identify outlier candidates, and then applies local outlier factor to calculate anomaly scores and detect theft. The performance of the presented method is evaluated on a realistic dataset.

Uploaded by

Arun K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 7

VISVESVARAYA TECHNOLOGICAL UNIVERSITY

Jnana Sangam, Machhe,Belagavi-590018

Technical Seminar Report on

“Electricity Theft Detection in AMI Based On Clustering And Local Outlier Factor”

Submitted in Partial fulfilment of


BACHELOR OF ENGINEERING DEGREE
IN
ELECTRICAL & ELECTRONICS ENGINEERING.
Submitted By

Ramesh Maddikar 2TG21EE408

Under the guidance of


Prof. Mallikarjun G. D B.E., M. Tech.
Assistant Professor
Dept. of Electrical & Electronics Engineering
TCE, Gadag

DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING


TONTADARYA COLLEGE OF ENGINEERING
MUNDARGI ROAD, GADAG-582 101
2023-2024

S.T.S.K. K’s

TONTADARYA COLLEGE OF ENGINEERING


MUNDARGI ROAD, GADAG – 582 101

DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING

CERTIFICATE
Certified that the Technical seminar work entitled “Electricity Theft Detection In AMI Based
On Clustering And Local Outlier Factor” carried out by Mr.Ramesh Maddikar,
USN:2TG21EE408, a bonafide student of Tontadarya College of Engineering, Gadag,
submitted the report, in partial fulfillment for the award of Bachelor of Engineering Degree in
Electrical & Electronics Engineering of the Visvesvaraya Technological University, Belagavi
during the year 2023-24.

It is also certified that all corrections/ suggestions indicated for Internal Assessment have been
incorporated in the report and deposited in the department library. The Technical Seminar
report has been approved as it satisfies the academic requirements in respect of Technical
Seminar Work prescribed for the said Degree.
Sign of the Guide Sign of the HoD Sign of the
Prof. Mallikarjun G. D Dr. Iranna Korachagaon. Dr. M. M. Awati.
Assistant Professor, HoD, Principal,
Dept. of Electrical & Electronics Dept. of Electrical & Electronics Engg.
TCE, Gadag.
Engg.

Principal

Acknowledgement
The satisfaction of successful completion of any task would be incomplete without the
expression of gratitude to the people who have made it possible. I/ We acknowledge all the
people who have guided and encouraged me/ us.

We would like to take this opportunity to thank our guide Prof. Mallikarjun G. D, and the
coordinator, Prof. J. G. Shivanagutti, Department of Electrical and Electronics Engineering, for
their immense guidance and support, without which this work would have been unthinkable.

I/ We also sincerely thank Dr. Iranna Korachagaon, HoD, Department of Electrical and
Electronics, TCE Gadag for his valuable suggestions and support.

I/ We extend our gratitude to Dr. M. M. Awati, Principal, TCE Gadag, for his generous support
in all regards.

I/ We extend our heartfelt thanks to all the faculty members, teaching and non-teaching staff of
Department of Electrical and Electronics Engineering, TCE Gadag, who have helped me/ us
directly or indirectly for the completion of this work.

Ramesh Maddikar 2TG21EE408


ABSTRACT
As one of the key components of smart grid, advanced metering infrastructure (AMI) provides
an immense number of data, making technologies such as data mining more suitable for
electricity theft detection. However, due to the unbalanced dataset in the field of electricity theft,
many AI-based methods such as deep learning are prone to under-fitting. To evade this problem
and to detect as many types of theft attacks as possible, an outlier detection method based on
clustering and local outlier factor (LOF) is proposed in this study. We firstly analyze the load
profiles with k-means. Then, customers whose load profiles are far from the cluster centers are
selected as outlier candidates. After that, the LOF is utilized to calculate the anomaly degrees of
outlier candidates. Corresponding framework for practical application is then designed. Finally,
numerical experiments based on realistic dataset show the good performance of the presented
method.
CONTENTS

Acknowledgement I
Abstract II
Contents III
List of figures IV
List of tables V
Table of abbreviation VI

CHAPTER 1: INTRODUCTION 1
1.1 Game Theory Based 1
1.2 System State Based 2
1.3 Power consumption pattern based 2
1.3.1 New techniques 3
1.3.2 Extensive experiments 3

CHAPTER 2: PROPOSED IMPEDENCE MATCHING


SOLUTION 4
2.1 Illustration on AMI system model 5
CHAPTER 3: METHODOLOGY 6
3.1.1. Local outlier factor 6
3.1.2 Illustration of the reachability distance 7
3.2 Clustering and local outlier factor 8
3.3 Detection framework 9
3.3.1 2-Dimensional outlier detection by CLOF 10
3.3.2 Framework of the CLOF detection method 11
CONCLUSION 12
REFERENCES 13
LIST OF FIGURES

Fig NO Details Page NO


FIG2.1 Illustration on AMI system model 5
FIG3.1 Illustration of the reachability distance 7
FIG3.2 2-Dimensional outlier detection by CLOF 10
FIG3.3 Framework of the CLOF detection method 11
TABLE OF ABBREVIATION
AMI Advanced Metering Infrastructure
ETDMs Electricity theft detection methods
NTL Non-technical loss
SVM Support vector machines
CNNs Convolutional neural networks
DBSCAN Density-based spatial clustering of applications with noise
LOF Local outlier factor
AI Artificial intelligence
FCM fuzzy C-means
LRD Local reachability density

You might also like