Application of binary particle swarm optimization in feature selection for transient stability assessment

For the disadvantage of traditional method in the feature selection of power system transient stability assessment, a new method is proposed based on binary particle swarm optimization (BPSO) algorithm. This method can find the model feature set that can reflect the physical natural characteristic of power system transient stability directly or indirectly and illustrate the system dynamic characteristic better. The proposed approach can reduce the input dimension by using Euclidean distance as the fitness function. The test on 8-machine 36-bus system of EPRI reveals the validity of the method mentioned.