A NEW ALGORITHM FOR KOHONEN LAYER LEARNING WITH APPLICATION TO POWER-SYSTEM STABILITY ANALYSIS

In certain classification problems, input patterns are not distributed in a clustering manner but distributed uniformly in an input space an d there exist certain critical hyperplanes called decision boundaries. Since learning vector quantization (LVQ) classifies an input vector b ased on the nearest neighbor, the codebook vectors away from the decis ion boundaries are redundant. This paper presents an alternative algor ithm called boundary search algorithm (BSA) for the purpose of solving this redundancy problem. The BSA finds a fixed number of codebook vec tors near decision boundaries by selecting appropriate training vector s. It is found to be more efficient compared with LVQ and its validity is demonstrated with satisfaction in the transient stability analysis of a power system.