Paper Details: Downloads: 550
Serial Number: P1111002963
Title: Enhancement of Multimachine Transient Stability Using Artificial Neural Network Based Phase Shifting Transformer
Authors: Ashraf Mohamed Hemeida, Ph.D. Associate Professor
Abstract: This paper aims to apply artificial neural network (ANN) based phase shifting transformer (PST) to enhance multi-machine power system transient stability. A new model of the phase shifting transformer based artificial neural network is proposed. The proposed model depends mainly on the function of the phase shifting transformer. The output machine voltages deviations, speed deviations and angles deviations are used as an input signal to the ANN model to provide phase advance for each machine voltage of the studied three machine six bus interconnected power system. The ANN model consists of input layer, hidden layer and output layer. The input layer consists of 6 input signals. The output layer consists of one signal which is the phase advance. The ANN offline training is made first to initialize the weights and bias matrix values. Hence, adaptive function of ANN is used as online ANN application to the studied multimachine power system to modify the weights and bias matrix according to the system dynamic performance. Different fault locations were considered to judge the effectiveness of the proposed ANN based PST. The time simulation results prove that the proposed ANN model based PST is very effective in improving the power system transient stability in case of severe disturbance such as unrepeated three-phase short circuit fault. A Comparative study between the conventional PST and ANN based PST proves the superiority of the proposed model. The studied power system is modeled and solved using the MATLAB software package.
Keywords: Transient Stability enhancement – Multi-machine Power System – Phase shifting transformer – Artificial neural network model
Journal/Conference: International Journal of Automatic Control and System Engineering
Volume: 10
Issue: 1
Submission Date: 1/2/2010 12:00:00 AM
Review Date: 12/12/2010 12:00:00 AM
Publishing Date: 3/2/2010 12:00:00 AM
Article Downloads: 550
Download:

Facebook