-
A. Bonini Neto
Faculdade de Ciências e Engenharia (FCE), Universidade Estadual Paulista (UNESP), Tupã, SP
-
C. C. de Oliveira
Instituto Federal do Amapá – IFAP – Centro de Referência Pedra Branca do Amapari, Macapá
-
D. A. Alves
Faculdade de Engenharia de Ilha Solteira (FEIS), Universidade Estadual Paulista (UNESP), Ilha Solteira, SP
-
C. R. Minussi
Faculdade de Engenharia de Ilha Solteira (FEIS), Universidade Estadual Paulista (UNESP), Ilha Solteira, SP
Keywords:
Continuation power flow, artificial intelligence, contingencies, P-V curves, mathematical modeling
Abstract
This work presents an approach using artificial neural networks (ANN) to obtain complete P-V curves of electrical power systems subjected to contingency. The differential of this methodology is in the speed in obtaining all the P-V curves of the system, under normal operating conditions or with contingencies. The great advantage of using ANN models is that they can capture the nonlinear characteristics of the studied system to avoid iterative procedures. From the results, the ANN performed well, with mean squared error in training below the specified value. From the samples that were not part of the training, the network was able to estimate 98% of the voltage magnitude values within the established range, with residues around 10-3 and a percentage of success between the desired and obtained output of approximately 97.3%.
