A Novel Electricity Theft Detection Scheme Based on Text Convolutional Neural Networks

Xiaofeng Feng,Hengyu Hui,Huakun Que,Yu Yao,Ziyang Liang,Wenchong Guo,Yi Ding,Haoyang Feng,Chengjin Ye

doi:10.3390/en13215758

Xiaofeng Feng, Hengyu Hui + Show 7 more

Open Access

https://doi.org/10.3390/en13215758

Copy DOI

Journal: Energies	Publication Date: Nov 3, 2020
Citations: 20	License type: CC BY 4.0

Affiliation: China Southern Power Grid (China), Zhejiang University

Abstract

Electricity theft decreases electricity revenues and brings risks to power usage’s safety, which has been increasingly challenging nowadays. As the mainstream in the relevant studies, the state-of-the-art data-driven approaches mainly detect electricity theft events from the perspective of the correlations between different daily or weekly loads, which is relatively inadequate to extract features from hours or more of fine-grained temporal data. In view of the above deficiencies, we propose a novel electricity theft detection scheme based on text convolutional neural networks (TextCNN). Specifically, we convert electricity consumption measurements over a horizon of interest into a two-dimensional time-series containing the intraday electricity features. Based on the data structure, the proposed method can accurately capture various periodical features of electricity consumption. Moreover, a data augmentation method is proposed to cope with the imbalance of electricity theft data. Extensive experimental results based on realistic Chinese and Irish datasets indicate that the proposed model achieves a better performance compared with other existing methods.

Highlights

Electricity theft can be defined as the behavior of illegally altering an electric energy meter to avoid billing
Based on the data structure, we propose a text convolutional neural network (TextCNN) to detect electricity theft
We propose a novel electricity theft detecting method based on text convolutional neural networks (TextCNN)

Summary

Introduction

Electricity theft can be defined as the behavior of illegally altering an electric energy meter to avoid billing. This illegal behavior severely disrupts the normal utilization of electricity, and causes huge economic losses to power systems. It is necessary to develop effective techniques for electricity theft detection and ensure the security and economic operation of power system. For different input data(DNN), types, The normal multilayered neural networks, which are called deep neural networks the structure of CNN should be layers selected further tolayers. Consist of input layers, hidden and output has an additional convolutional 26]. The discrete convolutiontime‐series, is the key operation in on convolutional layers.

Objectives

Results

Conclusion