Application of ANN for stability assessment of large power system by post-fault rotor angle measurements

Abstract

Dynamic Stability Assessment (DSA) of power system is a primary requirement in operation and control. Various methods of stability assessment have been reported in the past. In this paper, an Artificial Neural Network (ANN) based supervised learning architecture is presented to assess system stability. The architecture employs the post-fault values of generator rotor angle trajectory as input and predicts the final value of the rotor angle trajectory and time at which the critical generator will cross the system stability criteria. This supervised architecture assesses the radial basis function values of the input features and train the net for a large number of operating conditions with random duration fault at all bus and lines of the system. The results are validated on IEEE 10 Generator 39 bus test system. It is observed that the results obtained from this architecture are aligned with nonlinear simulation studies. The proposed method can be a beneficial tool for decision making at energy management center.