RAPID TRANSMISSION CAPACITY MARGIN DETERMINATION FOR DYNAMIC SECURITY ASSESSMENT USING ARTIFICIAL NEURAL NETWORKS

This paper presents a method for rapidly computing transmission capacity margin for security problems. The method uses an artificial neural network (ANN) to model a delineating surface between the region of security and the region of insecurity in the space of most critical parameters. If the number of critical parameters is two, the delineating 'surface' is simply the familiar nomogram line. In general, however, the delineating surface is multidimensional since the number of critical parameters for most security problems is greater than three. The margin to security limitations is computed as the solution to a nonlinear equality-constrained optimization problem, where the equality constraint is the operational boundary surface function, and the objective function is the shortest 'distance' between an operating point and the delineating surface.