Power Load Modeling Based on Wide-Area Measurements and Support Vector Machine

At present, the load modeling is still one of the difficult problems in power system. In this paper, a new method is presented which uses wide-area measurements and support vector machine (SVM) for load modeling. Based on wide-area measurements, this method does non-linear regression analysis on model with SVM. By using radial basis function (RBF), model structure is optimized, and Bayesian Framework is used for identifying parameters, then a kind of non-mechanical model is founded. This method can easily solve the problems in choosing structure and identifying parameters. The founded model has good generalization ability, flexible structure, and rapid calculation speed. In the end, this method has been programmed; the simulation verifies the validity of this model.