Prediction of critical clearing time using artificial neural network

Author

Olulope, P.K. ; Folly, K.A. ; Chowdhury, S.P. ; Chowdhury, S.

Author_Institution

Dept. of Electr. Eng., Univ. of Cape Town, Cape Town, South Africa

fYear

2011

fDate

11-15 April 2011

Firstpage

1

Lastpage

5

Abstract

This paper is concerned with the application of feed forward artificial neural networks for the prediction of the critical clearing time of a fault in power systems. The training of ANNs is done using selected features as inputs and the critical clearing time (CCT) as desire target. A single contingency was applied and the target CCT was found using time domain simulations. Multi layer feed forward neural network trained with Levenberg-Marquardt (LM) back propagation algorithm is used to provide the estimated CCT. The simulation results show that ANNs is capable to provide fast and accurate mapping. This makes it attractive for real-time stability assessment.

Keywords

backpropagation; feedforward neural nets; power engineering computing; power system faults; power system stability; time-domain analysis; ANN; CCT estimation; LM back propagation algorithm; Levenberg-Marquardt back propagation algorithm; critical clearing time prediction; feed forward artificial neural network; multilayer feed forward neural network; power system fault; real-time stability assessment; time domain simulations; Artificial neural networks; Mathematical model; Neurons; Power system stability; Stability analysis; Training; ANN; CCT; fault; stability;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence Applications In Smart Grid (CIASG), 2011 IEEE Symposium on

Conference_Location

Paris

Print_ISBN

978-1-4244-9893-2

Type

conf

DOI

10.1109/CIASG.2011.5953345

Filename

5953345