Transient stability prediction of power systems by a new synchronism status index and hybrid classifier

In this study, a new transient stability prediction method is proposed. The measured rotor angles of generators are first processed by a new non-linear transformation based on hyperbolic functions to construct a novel synchronism status index. The transformed rotor angles are then applied as input data to a hybrid classifier composed of an array of parallel probabilistic neural networks in which one probabilistic neural network is assigned to each unit of the power system. The proposed hybrid classifier can predict transient stability status of power system and determine tripped machines. The efficiency of the proposed solution method for transient stability prediction is studied based on the IEEE 162-bus and IEEE 145-bus test systems. Moreover, the effectiveness of the method under varied configurations of the power system is also shown.