Multi Layer Feed Forward Neural Network for Contingency Evaluation of Bulk Power System

This paper presents application of artificial neural network (ANN) based contingency analysis of bulk power system. The ANN has been chosen because of its high adaptation parallel information processing capability. Another feature that makes the ANN more suitable for this type of problems is its ability to augment new training data without the need for retraining. In this paper multilayer feed forward neural network is used for contingency analysis in planning studies where the goal is to evaluate the ability of a power system to support a projected range of peak demand under all foreseeable contingencies. This work involves selection of neural network, preparation of input training & testing patterns. In order to generate the training patterns two system topologies were considered. Training data are obtained by load flow studies (NR method) for different system topologies over a range of load levels using software simulation package (Mipower) and the results are compiled to form the training set. For training the ANN back propagation algorithm is used. The proposed algorithm is applied to an IEEE 14 bus bulk power system and the numerical results are presented to demonstrate the effectiveness of this proposed algorithm in terms of accuracy. It is concluded that the trained ANN can be utilized for both off-line simulation studies and on line estimation of line flows s. The software is developed using C language, which is user friendly.