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