Parameter Identification of Excitation Systems Based on Hopfield Neural Network

Liao, Qi; Liu, D.C.; Ying, Liming; Xue, Chengqi; Li, Y.; He, Wu

doi:10.1109/icpst.2006.321809

Cited by 4 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, many methods have been proposed to the excitation system parameter identification in recent years, such as genetic algorithm techniques (GA) [2,3], particle swarm optimization (PSO) [3,4], nonlinear least-square method [5], modified prony method [5], piecewise linear polynome function method (PLPF) [5], generalized least squares method (GLS) [6], and hopfield neural network techniques [7]. They have good performance on the excitation system parameter identification, but there is inadequates.…”

Section: Introductionmentioning

confidence: 99%

On-Line Parameters Identification for Excitation System Based on Small Population-Based Particle Swarm Optimization

2013

AMM

View full text Add to dashboard Cite

Parameters identification of excitation system plays a key role for the power system stability analysis. In this paper, a small population-based particle swarm optimization (SPPSO) approach is used to acquire excitation system on-line model quickly and accurately. In the proposed approaches, three operations are introduced to improve the performance of the algorithm, namely mutation operation, DE-acceleration operation and migration operation. Furthermore, the BPA-FV practical model and the PMU data are adopted. The simulation results of the model obtained by SPPSO have been compared with that of the model obtained by other approach in literature and our reformulations. The SPPSO algorithm shows better performance on the convergence as well as computation time and effort.

show abstract