A new constructive ANN and its application to electric load representation

Author

Da Silva, A. P Alves ; Ferreira, C. ; De Souza, A. C Zambroni ; Lambert-Torres, G.

Author_Institution

Escola Fed. de Engenharia de Itajuba, Brazil

Volume

12

Issue

4

fYear

1997

fDate

11/1/1997 12:00:00 AM

Firstpage

1569

Lastpage

1575

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

Keywords

load (electric); neural nets; power system analysis computing; substations; 138 kV; artificial neural network; computer simulation; functional polynomial network; load chaotic behavior; nonparametric load model; parametric load model based; power system dynamic load models; substation buses; Artificial neural networks; Chaos; Load management; Load modeling; Polynomials; Power system control; Power system dynamics; Power system modeling; Power system stability; System identification;

fLanguage

English

Journal_Title

Power Systems, IEEE Transactions on

Publisher

ieee

ISSN

0885-8950

Type

jour

DOI

10.1109/59.627860

Filename

627860