Real-Time Detection of Power Quality Disturbance Using Fast Fourier Transform and Adaptive Neuro-Fuzzy Inference System

Abstract

Power quality disturbances cause equipment damage or financial losses. Therefore, the electric power system needs to identify and distinguish any power quality disturbances to reduce problems. This paper proposes hybrid methods combining FFT and ANFIS algorithm for detection of power quality disturbances. There are 11 types of power quality disturbances that can be detected, such as sag, swell, undervoltage, overvoltage, voltage flicker, voltage harmonic, sag + harmonic, swell + harmonic, undervoltage + harmonic, overvoltage + harmonic, and flicker + harmonic. The parameters used to detect disturbances are Vrms, Duration, THDv (Total Harmonic Distortion voltage), and Fluctuation-Count. The detection process starts by sensing voltage and calculating all the parameters, where THDv was obtained by Fast Fourier Transform. All the parameters such as Vrms, Duration, THDv, and Fluctuation-Count are processed by Adaptive Neuro-Fuzzy Inference System, and the result is the type of disturbance. Matlab simulations show that the suggested method performs outstandingly to identify 11 type of Power Quality Disturbances with 99.3% accuracy.