Online Static Security Assessment Module Using Artificial Neural Network on IEEE-30 Bus Test System?

Maintaining system security is an important aspect in the operation of the power system. Security status, contingency screening and ranking are one of the most important issues in the static security assessment. By using Newton Raphson method composite security index is calculated. For different operating condition, artificial neural network (ANN) is trained by considering limiting violation factor. Two types of ANN are used; they are Multilayer feed forward neural network (MLFFN) and Radial basis function network (RBFN). The objective of this paper is to rank the critical contingencies more quickly and accurately from the large list of potential contingencies according to the order of severity in the decreasing order. The proposed method is applied to IEEE 30-bus test system. Composite security index (CSI) based on Newton Raphson load flow (NRLF) analysis is compared with MLFFN and RBFN. Computation speed will be less for ANN methods. Online static security assessment (OSSA) module realized using the ANN models are found to be suited for online application.