Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems (Changes are marked)

Created by
  • Haebom

Author

Javad Enayati, Pedram Asef, Alexandre Benoit

Outline

This paper presents a novel hybrid AI method combining an H-filter and an adaptive linear neural network for flicker component estimation in power distribution systems. This method leverages the robustness of the H-filter to extract the voltage envelope under uncertain and noisy conditions, followed by ADALINE to accurately identify the flicker frequency contained within the envelope. This synergy enables efficient time-domain estimation with fast convergence and noise resilience, addressing the key limitations of existing frequency-domain methods. Unlike existing techniques, this hybrid AI model handles complex power disturbances without prior knowledge of noise characteristics or extensive training. The performance of the method is validated using simulation studies based on IEC standard 61000-4-15, statistical analysis, Monte Carlo simulations, and real-world data. The results demonstrate superior accuracy, robustness, and reduced computational overhead compared to estimators based on the Fast Fourier Transform and Discrete Wavelet Transform.

Takeaways, Limitations

•
Takeaways:
◦
Improving the efficiency and accuracy of flicker component estimation using a hybrid AI model of H-filter and ADALINE.
◦
Presenting the possibility of real-time flicker monitoring with robustness to noise and fast convergence speed.
◦
Solving the problem of complex power disturbance handling, which is a limitation of existing frequency domain methods.
◦
Effective flicker estimation without prior knowledge or extensive training.
◦
Demonstrates superior performance (accuracy, robustness, computational load) over FFT and DWT-based methods.
•
Limitations:
◦
Lack of specific information about the type and scale of actual data presented in the paper.
◦
Further research is needed on generalization performance for different types of flicker and power disturbances.
◦
Further verification of the proposed method's application to actual power systems is needed.
◦
Lack of detailed explanation of parameter optimization of H filter and ADALINE.
👍
Made with Slashpage