Approximate Loading Margin Methods Using Artificial Neural Networks in Power Systems

Abstract

This paper proposes approximate loading margin methods using Artificial Neural Networks (NN) for static voltage stability in power systems. Two methodologies, namely Actual LM with NN (ALM-NN) and Maximum Loading Margin with NN (MLM-NN), are proposed for finding NN training data sets. Artificial Neural Network is used to approximate the loading margin at particular generation direction. The proposed methods are validated and compared with the Maximum Loading Margin method in the modified IEEE 14-bus test system. The methods will help system operators to approximate voltage stability margin or loading margin of the system in a short period of time.