Neural network based classification method for small-signal stability assessment

This paper deals with a new method for eigenvalue prediction of critical stability modes of power systems based on neural networks. Special interest is focused on inter-area oscillations of large-scale interconnected power systems. The existing methods for eigenvalue computations are time-consuming and require the entire system model that comprises an extensive number of state variables. After reduction of the neural network input space and proper training of the neural network, it predicts the stability condition of the power system with high accuracy. A byproduct of this research is the development of a new 16-machine dynamic test system.