Nonlinear identification of the external power system dynamic equivalent for the study system

Based on the concept of the external power system dynamic equivalent for the study system, in this paper a reduced-order artificial neural network is proposed, which is constructed to model the external part. The mastermind behind the proposed method is to identify the external part as a dynamic-algebraic ANN, and this separation between dynamic equations in the state space form and algebraic equations is useful to solve the prediction problem. To obtain this model, the system should be excited by some disturbances, and according to the measured data on the boundary nodes, identification procedure is accomplished. Therefore, the trained network can be used to predict behavior of the external system in a high degree of accuracy.