Artificial neural networks applied to reliability and well-being assessment of composite power systems

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2008

Autores

Armando M. Leite da Silva (Autor) Outra; Leonidas C. de Resende (Autor) Outra; Luiz A. da Fonseca Manso (Autor) Outra; Vladimiro Miranda (Autor) FEUP

Ata de Conferência Internacional

Título: 2008 10TH INTERNATIONAL CONFERENCE ON PROBABILISTIC METHODS APPLIED TO POWER SYSTEMS

Páginas: 310-315

10th International Conference on Probabilistic Methods Applied to Power Systems

Rincon, PR, MAY 25-29, 2008

Indexação

ISI Web of Knowledge - 0 Citações

ISI Web of Science

Scopus - 3 Citações

INSPEC

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Engenharia electrotécnica, electrónica e informática

Outras Informações

ID Authenticus: P-007-R0H

Abstract (EN): This paper presents a new methodology for assessing both reliability and well-being indices for composite generation and transmission systems. Firstly, a transmission network reduction is applied to find an equivalent for assessing composite reliability for practical large power systems. After that, in order to classify the operating states, Artificial Neural Networks (ANNs) based on Group Method Data Handling (GMDH) techniques are used to capture the patterns of the operating states, during the beginning of the non-sequential Monte Carlo simulation (MCS). The idea is to provide the simulation process with an intelligent memory, based only on polynomial parameters, to speed up the evaluation of the operating states. For the conventional reliability assessment, the ANNs are used to classify the operating states into success and failure. However, for the well-being analysis, only success states are classified into healthy and marginal by the ANNs. The proposed methodology is applied to the IEEE Reliability Test System 1996 and to a configuration of the Brazilian South-Southeastern System.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6