Publicação

Hydrogen consumption prediction of a fuel cell based system with a hybrid intelligent approach

Ver documento

Detalhes bibliográficos
Resumo:Energy storage is one of the challenges of the electric sector. There are several different technologies available for facing it, from the traditional ones to the most advanced. With the current trend, it is mandatory to develop new energy storage systems that allow optimal efficiency, something that does not happen with traditional ones. Another feature that new systems must meet is to envisage the behaviour of energy generation and consumption. With this aim, the present research deals the hydrogen consumption prediction of a fuel cell based system thanks a hybrid intelligent approach implementation. The work is based on a real testing plant. Two steps have been followed to create a hybrid model. First, the real dataset has been divided into groups whose elements have similar characteristics. The second step, carry out the regression using different techniques. Very satisfactory results have been achieved during the validation of the model.
Autores principais:Montero-Sousa, Juan Aurelio
Outros Autores:Aláiz-Moretón, Héctor; Quintián, Héctor; González-Ayuso, Tomás; Novais, Paulo; Calvo-Rolle, José Luis
Assunto:ANN BHL Energy management Energy storage Fuel cell SVM
Ano:2020
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
Descrição
Resumo:Energy storage is one of the challenges of the electric sector. There are several different technologies available for facing it, from the traditional ones to the most advanced. With the current trend, it is mandatory to develop new energy storage systems that allow optimal efficiency, something that does not happen with traditional ones. Another feature that new systems must meet is to envisage the behaviour of energy generation and consumption. With this aim, the present research deals the hydrogen consumption prediction of a fuel cell based system thanks a hybrid intelligent approach implementation. The work is based on a real testing plant. Two steps have been followed to create a hybrid model. First, the real dataset has been divided into groups whose elements have similar characteristics. The second step, carry out the regression using different techniques. Very satisfactory results have been achieved during the validation of the model.