A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems

TL;DR

This paper presents a hybrid AI approach combining H filtering and ADALINE neural networks for accurate, noise-robust flicker estimation in power systems, outperforming traditional frequency domain methods in accuracy and efficiency.

Contribution

The paper introduces a novel hybrid AI method that effectively estimates flicker in power systems without prior noise knowledge, improving accuracy and computational efficiency.

Findings

Superior accuracy over FFT and DWT methods

Enhanced robustness to noise and disturbances

Reduced computational load in flicker estimation

Abstract

This paper introduces a novel hybrid AI method combining H filtering and an adaptive linear neuron network for flicker component estimation in power distribution systems.The proposed method leverages the robustness of the H filter to extract the voltage envelope under uncertain and noisy conditions followed by the use of ADALINE to accurately identify flicker frequencies embedded in the envelope.This synergy enables efficient time domain estimation with rapid convergence and noise resilience addressing key limitations of existing frequency domain approaches.Unlike conventional techniques this hybrid AI model handles complex power disturbances without prior knowledge of noise characteristics or extensive training.To validate the method performance we conduct simulation studies based on IEC Standard 61000 4 15 supported by statistical analysis Monte Carlo simulations and real world data.Results demonstrate superior accuracy robustness and reduced computational load compared to Fast Fourier Transform and Discrete Wavelet Transform based estimators.