Superiority of decision tree classifier on complicated cases for power system protection

Özgönenel O., Thomas D., Yalcin T.

11th IET International Conference on Developments in Power Systems Protection, DPSP 2012, Birmingham, England, 23 - 26 April 2012, vol.2012, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 2012
  • Doi Number: 10.1049/cp.2012.0054
  • City: Birmingham
  • Country: England
  • Keywords: continuous wavelet transform (CWT), Decision tree, power distortions, protection, quality issues
  • Ondokuz Mayıs University Affiliated: Yes

Abstract

Diagnosis of power system faults requires identification and classification of voltage disturbances in power systems and smart grids. The objective of this approach is to develop state of art signal classification algorithms for classifying different types of power quality disturbances (faults) based on latest improvements in signal processing and pattern recognition techniques. This paper proposes a new solution for power system monitoring against all possible power quality issues. S-transform is used for analyzing distorted power signal. As a classifier, decision tree algorithm is used and its performance is compared to other classifiers. The proposed hybrid power system monitoring system is able to detect common power system disturbances such as voltage sag/swell/, flicker, DC component, electro-magnetic interference, harmonics, transients and blackouts.