Title: Application of soft computing neural network tools to line congestion study of electrical power systems

Authors: Pradyumna Kumar Sahoo; Prasanta Kumar Satpathy; Srikanta Patnaik

Addresses: ITER, EE Department, S'O'A University, Bhubaneswar, Odisha, India ' EE Department, College of Engineering and Technology, Bhubaneswar, Odisha, India ' Dept. of CSE, ITER, S'O'A University, Bhubaneswar, Odisha, India

Abstract: This paper presents a scheme for application of soft computing neural network tools namely feed forward neural network with backpropagation, and radial basis function neural network for the study of transmission line congestion in electrical power systems. The authors performed sequential training of the two proposed neural networks for monitoring the level of line congestion in the system. Finally, a comparative analysis is drawn between the two neural networks and it is observed that radial basis function neural network yields fastest convergence. The proposed method is tested on the IEEE 30-bus test system subject to various operating conditions.

Keywords: line congestion index; LCI; neural network; hidden layer; training performance.

DOI: 10.1504/IJICT.2018.090559

International Journal of Information and Communication Technology, 2018 Vol.13 No.2, pp.219 - 226

Received: 23 May 2015
Accepted: 12 Aug 2015
Published online: 22 Mar 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article