Utilize este identificador para referenciar este registo: https://hdl.handle.net/10216/92435
Autor(es): J. Nuno Fidalgo
João Torres
Manuel A. Matos
Título: Fair allocation of distribution losses based on neural networks
Data de publicação: 2007
Resumo: In a competitive energy market environment, the procedure for fair loss allocation constitutes a matter of considerable importance. This task is often based on rough principles, given the difficulties on the practical implementation of a fairest process. This paper proposes a methodology based on neural networks for the distribution of power distribution losses among the loads. The process is based on the knowledge of load profiles and on the usual consumption measures. Simulations ere carried out for a typical MV network, with an extensive variety of load scenarios. For each scenario, losses were calculated and distributed by the consumers. The allocation criterion is established assuming a distribution proportional to the squared power. Finally, a neural network is trained in order to obtain a fast and accurate losses allocation. Illustrative results support the feasibility of the proposed methodology.
Assunto: Engenharia electrotécnica, electrónica e informática
Electrical engineering, Electronic engineering, Information engineering
Áreas do conhecimento: Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática
Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
URI: https://repositorio-aberto.up.pt/handle/10216/92435
Fonte: 2007 INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS APPLICATIONS TO POWER SYSTEMS, VOLS 1 AND 2
Tipo de Documento: Artigo em Livro de Atas de Conferência Internacional
Condições de Acesso: restrictedAccess
Aparece nas coleções:FEUP - Artigo em Livro de Atas de Conferência Internacional

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
60470.pdf
  Restricted Access
276.91 kBAdobe PDF    Request a copy from the Author(s)


Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.