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

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%.