Performance Analysis of Different Types of Machine Learning Classifiers for Non-Technical Loss Detection

Khawaja Moyeezullah Ghori,Laszlo Szathmary,Muhammad Imran,Ata Ullah,Muhammad Awais,Rabeeh Ayaz Abbasi

doi:10.1109/access.2019.2962510

Abstract

With the ever-growing demand of electric power, it is quite challenging to detect and prevent Non-Technical Loss (NTL) in power industries. NTL is committed by meter bypassing, hooking from the main lines, reversing and tampering the meters. Manual on-site checking and reporting of NTL remains an unattractive strategy due to the required manpower and associated cost. The use of machine learning classifiers has been an attractive option for NTL detection. It enhances data-oriented analysis and high hit ratio along with less cost and manpower requirements. However, there is still a need to explore the results across multiple types of classifiers on a real-world dataset. This paper considers a real dataset from a power supply company in Pakistan to identify NTL. We have evaluated 15 existing machine learning classifiers across 9 types which also include the recently developed CatBoost, LGBoost and XGBoost classifiers. Our work is validated using extensive simulations. Results elucidate that ensemble methods and Artificial Neural Network (ANN) outperform the other types of classifiers for NTL detection in our real dataset. Moreover, we have also derived a procedure to identify the top-14 features out of a total of 71 features, which are contributing 77% in predicting NTL. We conclude that including more features beyond this threshold does not improve performance and thus limiting to the selected feature set reduces the computation time required by the classifiers. Last but not least, the paper also analyzes the results of the classifiers with respect to their types, which has opened a new area of research in NTL detection.

Highlights

Non-Technical Loss (NTL) is the loss incurred due to the unlawful theft attempts by the malicious consumers of electricity
Other methods include direct hooking from the main lines, reversing the meter units after opening electric meter, using magnetic device to slow down the normal rotation of units disc, changing the direction of meter to stop the rotation of units disc and tapping the neutral wire in the meter to stop the normal rotation of units disc [4]
CatBoost [49], Light Gradient Boosting Machine (LGBoost) [51] and XGBoost [52] are open source libraries which are available in GitHub for Python

Summary

Introduction

Non-Technical Loss (NTL) is the loss incurred due to the unlawful theft attempts by the malicious consumers of electricity. With the ever-growing demand of electricity, NTL identification is becoming mandatory to protect illegal theft of electricity which can save billions of dollars [1]. Brazil suffers 4.5 billion dollars annually due to NTL [3]. Pakistan’s economy is suffering from 0.89 billion dollars annually on account of. NTL [4], which is mostly caused due to bypassing electric meter, which results in zero meter reading for the consumer. The meter reader is involved in malfunctioning the meter, which results in near-zero reporting of NTL. This becomes a dilemma for the power supply company as it becomes hard to identify individual households where NTL is happening.

Objectives

Methods

Results

Conclusion