Dynamic load modeling based on a nonparametric ANN

Abstract

Accurate dynamic load models allow more precise calculations of power system controls and stability limits. System identification methods can be applied to estimate load models based on measurements. Parametric and nonparametric (functional) are the two main classes in system identification methods. The parametric approach has been the only one used for load modeling so far. In this paper, the performance of a functional load model based on a polynomial artificial neural network is compared with a linear model and with the popular "ZIP" model. The impact of clustering different load compositions is also investigated. Substation buses (138 kV) from the Brazilian system feeding important industrial consumers have been modelled.