Título: A Neural Network for Transient Stability Analysis and Preventive Control of Eletric Energy Systems
Autores: Lotufo, Anna Diva P.; Lopes, Mara Lúcia Martins; Minussi, Carlos R.
Resumo: This work presents a procedure for transient stability analysis and for preventive control of eletric power systems, formulated by multilayer feedforward neural network training is realised using the fuzzy controller is used to provide a faster convergence and more precise results, if compared to the traditional backpropagation algorithm. The adapting of the training rate, is effectuated using the information of the global error, and global error variation. After finishing the training, the neural network is capable to estimate the security margin, and the sensitivy analysis. With these information it is possible to develop a method for the realisation of the security corretion (preventive control)for levels considered appropriate to the system,based on generation reallocation and load shedding. To illustrate the proposed methodology it is presented an aplication considerning a multi-machine power system.
Código DOI: 10.21528/CBRN2003-023
Artigo em PDF: 6CBRN_023.PDF
Arquivo BibTex: 6CBRN_023.bib