Classification of power quality disturbances using wavelet transform and SVM decision tree

Author

Milchevski, Aleksandar ; Taskovski, Dimitar

Author_Institution

Fac. of Electr. Eng. & Inf. Technol., Ss Cyril & Methodius Univ. - Skopje, Skopje, Macedonia

fYear

2011

fDate

17-19 Oct. 2011

Firstpage

1

Lastpage

5

Abstract

In this paper we present a new method for detection and classification of power quality disturbances. For the feature extraction process we use wavelet analysis. However, the feature vector is extended with three additional features which make the classification more accurate. For the classification of the power disturbances we use SVM (Support Vector Machine). According to the properties of the analyzed power disturbances binary decision tree is created and a SVM model for every node in the tree is performed. The obtained experimental results show high accuracy of the algorithm that is very close to 100%.

Keywords

feature extraction; power supply quality; support vector machines; wavelet transforms; SVM decision tree; feature extraction process; power quality disturbances; support vector machine; wavelet analysis; wavelet transform; Feature extraction; Power quality; Support vector machine classification; Wavelet analysis; Wavelet transforms; SVM; pattern classification; power quality; wavelets;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Power Quality and Utilisation (EPQU), 2011 11th International Conference on

Conference_Location

Lisbon

ISSN

2150-6647

Print_ISBN

978-1-4673-0379-8

Type

conf

DOI

10.1109/EPQU.2011.6128922

Filename

6128922