A NEURAL-NETWORK-BASED APPROACH FOR ONLINE DYNAMIC STABILITY ASSESSMENT USING SYNCHRONIZING AND DAMPING TORQUE COEFFICIENTS

This paper presents an artificial neural network (ANN)-based on-line a pproach to evaluate the dynamic stability of a single machine infinite bus system. The proposed on-line assessment scheme is based on estima ting the synchronizing and damping torque coefficients as dynamic perf ormance indices. The two performance indices are estimated from on-lin e measurements of the changes in the rotor angle, speed and electromag netic torque using a three-layer feedforward neural network with back propagation. The results show that the proposed method is very promisi ng and encouraging for fast real-time evaluation of the dynamic perfor mance of power systems. (C) 1996 Elsevier Science S.A.