Radial basis function networks for power system dynamic load modeling

The importance of electric load models in power system transient stability studies has long been recognized. In this paper the radial basis function network (RBFN) is presented for dynamic load modeling. The learning algorithm for RBFN is based on first choosing the RBF centers using the K-means clustering method and then using singular value decomposition to obtain the parameters. Its fast training procedure and high precision makes it more appropriate for power system dynamic load modeling. The simulation results of the field and laboratory tests demonstrate that the application of the RBFN is promising.<>