Artificial neural networks for real-time estimation of basic waveforms of voltages and currents

Author

Cichocki, A. ; Lobos, T.

Author_Institution

Tech. Univ. Warsaw, Poland

Volume

9

Issue

2

fYear

1994

fDate

5/1/1994 12:00:00 AM

Firstpage

612

Lastpage

618

Abstract

New parallel algorithms for the estimation of the parameters of a power system sinewave contaminated by noise are proposed. The problem of estimation is formulated as an optimization problem and solved by using the gradient descent method. Algorithms based on the least absolute value, the least-squares and the minimax (Chebyshev) criteria are developed and compared. The implementation of the algorithms by an appropriate neural network is also given. Illustrative computer simulation results confirm validity and high performance of the proposed solution

Keywords

Chebyshev approximation; digital simulation; least squares approximations; minimax techniques; neural nets; optimisation; parameter estimation; power supply quality; power system analysis computing; real-time systems; Chebyshev criteria; algorithm; artificial neural networks; computer simulation; current waveform; gradient descent method; least absolute value; least-squares criteria; minimax criteria; optimization; parameter estimation; performance; real-time; sinewave; voltage waveform; Artificial neural networks; Distortion measurement; Minimax techniques; Neural networks; Noise measurement; Parameter estimation; Power system protection; Signal processing; Signal processing algorithms; Voltage;

fLanguage

English

Journal_Title

Power Systems, IEEE Transactions on

Publisher

ieee

ISSN

0885-8950

Type

jour

DOI

10.1109/59.317683

Filename

317683