An Implementation of Exploratory Start for Power Quality Disturbance Pattern Recognition

Abstract

Identification of system disturbances and detection of them guarantees smart grids power quality system reliability and long lasting life of the power system. The key goal of this study is to generate non - time consuming features for CPU, for recognizing different types of non-stationary and non-linear smart grid faults based on signal processing techniques. This paper proposes a new solution for real time power system monitoring against power quality faults focusing on voltage sag and noise. EEMD is used for noise reduction with first intrinsic mode function (imf1). Hilbert Huang Transform (HHT) is used for generating instantaneous amplitude (IA) and instantaneous frequency (IF) feature of real time voltage sag power signal. The proposed power system monitoring system is able to detect power system voltage sag disturbances and capable of recognize and remove EMI (Electromagnetic Interference)-Noise.  In this study based on experimental studies, Hilbert Huang based pattern recognition technique was used to investigate power signal to diagnose voltage sag in power grid. SVM and Decision Tree (C4.5) were operated and their achievements were matched for calculation error and CPU time. According to the analysis, decision tree algorithm without dimensionality reduction produces the best solution.