Artificial neural networks based steady state security analysis of power systems

Abstract

The focus of this paper is to present an artificial neural network based methodology to assess the steady state security of a power system. The security of the system is assessed on the basis of the voltage profile at each bus with reference to changes in generation and load in the system. The input to the neural network is the voltage level at each bus. The ANN used is a feedforward multilayer network trained with a backpropagation algorithm. The output of the ANN classifies the security of the power system into normal, alert and emergency states. An IEEE 14-bus system is considered to demonstrate the results of the methodology.