A new constructive ANN and its application to electric load representation

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 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 nonparametric load model based on a new constructive artificial neural network (functional polynomial network) is compared with a linear model and with the popular ZIP model. The impact of clustering different load compositions is also investigated. A comparison among the models' performance for load chaotic behavior is presented, and some important conclusions are addressed. Substation buses (138 kV) from the Brazilian power system feeding important industrial consumers have been modeled.