Minimum frequency prediction of power system after disturbance based on the v-support vector regression

The prediction of power system minimum frequency after disturbance is the main content of power system measures. This paper presents a method based on the v-SVR to predict the minimum frequency and the frequency dynamic rapidly after disturbance. Several conditions which have effects on the power system frequency dynamic, such as the maximum output limit of the generator, spinning reserve levels and its distribution, turbine-governor, load et al. The method presented in this paper is accurate and quick enough to predict the frequency dynamic and its minimum value, and the method is based on support vector regression which is of good generalization ability and extension. Furthermore, the method presented in this paper can be used online for power system frequency stability assessment.