Radial Basis Function Neural Network for Power System Transient Energy Margin Estimation

Abstract

This paper presents a method for estimating the transient stability status of the power system using radial basis function (REF) neural network with a fast hybrid training approach. A normalized transient energy margin (ΔV n ) has been obtained by the potential energy boundary surface (PEES) method along with a time-domain simulation technique, and is used as an output of the REF neural network. The REF neural network is then trained to map the operating conditions of the power system to the ΔV n , which provides a measure of the transient stability of the power system. The proposed approach has been successfully applied to the 10-machine 39-bus New England test system, and the results are given.