What is the importance of selecting features for non-technical losses identification?

Author

Ramos, Caio C O ; Papa, João P. ; Souza, André N. ; Chiachia, Giovani ; Falcão, Alexandre X.

Author_Institution

Dept. of Electr. Eng., Univ. of Sao Paulo, Sao Paulo, Brazil

fYear

2011

fDate

15-18 May 2011

Firstpage

1045

Lastpage

1048

Abstract

Although non-technical losses automatic identification has been massively studied, the problem of selecting the most representative features in order to boost the identification accuracy has not attracted much attention in this context. In this paper, we focus on this problem applying a novel feature selection algorithm based on Particle Swarm Optimization and Optimum-Path Forest. The results demonstrated that this method can improve the classification accuracy of possible frauds up to 49% in some datasets composed by industrial and commercial profiles.

Keywords

electricity supply industry; fraud; particle swarm optimisation; pattern classification; power consumption; classification accuracy; commercial profiles; feature selection algorithm; frauds; identification accuracy; industrial profiles; nontechnical losses automatic identification; nontechnical losses identification; optimum-path forest; particle swarm optimization; representative features; Accuracy; Bismuth; Libraries; Particle swarm optimization; Power systems; Prototypes; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems (ISCAS), 2011 IEEE International Symposium on

Conference_Location

Rio de Janeiro

ISSN

0271-4302

Print_ISBN

978-1-4244-9473-6

Electronic_ISBN

0271-4302

Type

conf

DOI

10.1109/ISCAS.2011.5937748

Filename

5937748