KOHONEN NEURAL NETWORK CLASSIFIER FOR VOLTAGE COLLAPSE MARGIN ESTIMATION

Abstract

ABSTRACT Owing to frequent black-outs world wide, voltage collapse has received much attention in the electric utilities industry. This paper presents an artificial neural network based method for on-line voltage collapse margin estimation. Homotopy Continuation based Newton-Raphson method is used to drive system operating point to knee of nose curve. The distance of operating point from critical point, measured in terms of system loading may be regarded as margin to voltage collapse. This paper utilizes Kohonen classifier to estimate margin so that computational efforts are reduced compared to conventional methods. Also there is ample of saving in training time compared to error back propagation for parameter estimation. Kohonen neural network classifier transforms input patterns into neurons on the 2-dimensional grid. Power system conditions are assigned to neurons on the grid based on self-organized feature mapping. Finally these neurons are allocated voltage collapse margins corresponding to their system conditions representation. The effectiveness of the proposed technique is tested on sample systems.