A Novel Features-Based Multivariate Gaussian Distribution Method for the Fraudulent Consumers Detection in the Power Utilities of Developing Countries

Ammar Yousaf Kharal,Hassan Abdullah Khalid,Adel Gastli,Josep M Guerrero

doi:10.1109/access.2021.3085501

Ammar Yousaf Kharal, Hassan Abdullah Khalid + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3085501

Copy DOI

Abstract

According to statistics, developing countries all over the world have suffered significant non-technical losses (NTLs) both in natural gas and electricity distribution. NTLs are thought of as energy that is consumed but not billed e.g., theft, meter tampering, meter reversing, etc. The adaptation of smart metering technology has enabled much of the developed world to significantly reduce their NTLs. Also, the recent advancements in machine learning and data analytics have enabled a further reduction in these losses. However, these solutions are not directly applicable to developing countries because of their infrastructure and manual data collection. This paper proposes a tailored solution based on machine learning to mitigate NTLs in developing countries. The proposed method is based on a multivariate Gaussian distribution framework to identify fraudulent consumers. It integrates novel features like social class stratification and the weather profile of an area. Thus, achieving a significant improvement in fraudulent consumer detection. This study has been done on a real dataset of consumers provided by the local power distribution companies that have been cross-validated by onsite inspection. The obtained results successfully identify fraudulent consumers with a maximum success rate of 75%.

Highlights

Non-technical losses (NTLs) are considered as the energy that has flowed through the electricity and gas distribution networks to the end consumer but is not billed
This study uses monthly consumption datasets for electricity and natural gas from the Lahore Electricity Supply Company (LESCO) and Sui Northern Gas Pipelines Limited (SNGPL) from which some sample data is presented in Figure. 8(b) and (d), respectively
The data of all localities get combined into one data set and is passed on to the fraudulent consumer identification framework (FCIF)

Summary

Introduction

Non-technical losses (NTLs) are considered as the energy that has flowed through the electricity and gas distribution networks to the end consumer but is not billed . These non-billing issues are usually caused by fraudulent activities such as theft, tampering of metering equipment, violating tariff obligations, etc. Both the developed and developing countries suffer from these NTLs. the remedies employed by the developed countries do not apply to developing countries due to scarce resources and cost constraints. Some prevalent reasons leading to fraud and its types in the electricity and gas distribution networks of the developing countries are presented in Table 1 [3], [4]

Methods

Results

Conclusion