Solar Intensity Forecasting using Artificial Neural Networks and Support Vector Machines

This paper presents several forecasting methodologies based on the application of Artificial Neural Networks (ANN) and Support Vector Machines (SVM), directed to the prediction of the solar radiance intensity. The methodologies differ from each other by using different information in the training of the methods, i.e, different environmental complementary fields such as the wind speed, temperature, and humidity. Additionally, different ways of considering the data series information have been considered. Sensitivity testing has been performed on all methodologies in order to achieve the best parameterizations for the proposed approaches. Results show that the SVM approach using the exponential Radial Basis Function (eRBF) is capable of achieving the best forecasting results, and in half execution time of the ANN based approaches.

A contribuição de um sistema solar térmico no desempenho energético do edifício solar XXI

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa Para a obtenção do Grau de Mestre em Energia e Bioenergia

Fotocatálise solar para tratamento de águas de captação

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Química e Bioquímica

Desinfestação de diferentes tipos de papel utilizando o calor solar: estudo dos seus efeitos em estufa e aplicação sob diferentes condições climatéricas

Dissertação de Mestrado em Conservação e Restauro área de especialização: Documentos Gráficos

Optimização térmica de um sistema de concentração solar fotovoltaico

Dissertação para obtenção do Grau de Mestre em Engenharia de Materiais

Avaliação do impacte das pontes térmicas no desempenho térmico dos edifícios do Campus da FCT/UNL – análise experimental

Dissertação apresentada à Faculdade de Ciências e Tecnologias da Universidade Nova de Lisboa para obtenção do grau Mestre em Engenharia Civil – Reabilitação de Edifícios

Avaliação do impacte das pontes térmicas no desempenho térmico dos edifícios do Campus da FCT/UNL - análise numérica

Dissertação apresentada na Faculdade de Ciências e Tecnologias da Universidade Nova de Lisboa para obtenção do grau Mestre em Engenharia Civil – Reabilitação de Edifícios

Design of the ISePorto robocup Middle-Size League Robotic Soccer Team: Control, Localisation and Coordination

Proceedings of the 10th Mediterranean Conference on Control and Automation - MED2002 Lisbon, Portugal, July 9-12, 2002

Control and Localisation for the ISePorto Robotic Soccer Team

International Conference on Advanced Robotics, Coimbra, Portugal, Julho 2003

ISePorto Robotic Soccer Team: A New Player Generation

Proceedings of the Scientific Meeting of the Portuguese Robotics Open 2004

Viabilidade da aplicação da energia solar no reaquecimento de uma central termoeléctrica

Dissertação para a obtenção do Grau de Mestre em Engenharia Mecânica

Desenvolvimento de um concentrador solar fixo para foto-estimulação

Dissertação para obtenção do grau de Mestre em Engenharia Biomédica

Integração de dados LIDAR com imagens de muito alta resolução espacial para determinação de áreas urbanas com potencial solar

Dissertação apresentada para cumprimento dos requisitos necessários à obtenção do grau de Mestre em Gestão do Território, área de especialização em Detecção Remota e SIG

Anomalous persistent photoconductivity in Cu2ZnSnS4 thin films and solar cells

A persistent photoconductivity effect (PPC) has been investigated in Cu2ZnSnS4 thin films and solar cells as a function of temperature. An anomalous increase of the PPC decay time with temperature was observed in all samples. The PPC decay time activation energy was found to increase when temperature rises above a crossover value, and also to grow with the increase of the sulfurization temperature and pressure. Both the anomalous behavior of the PPC decay time and the existence of two different activation energies are explained in terms of local potential fluctuations in the band edges of CZTS.

A comparison between thin film solar cells made from co-evaporated CuIn1-xGaxSe2using a one-stage process versus a three-stage process

Until this day, the most efficient Cu(In,Ga)Se2 thin film solar cells have been prepared using a rather complex growth process often referred to as three-stage or multistage. This family of processes is mainly characterized by a first step deposited with only In, Ga and Se flux to form a first layer. Cu is added in a second step until the film becomes slightly Cu-rich, where-after the film is converted to its final Cu-poor composition by a third stage, again with no or very little addition of Cu. In this paper, a comparison between solar cells prepared with the three-stage process and a one-stage/in-line process with the same composition, thickness, and solar cell stack is made. The one-stage process is easier to be used in an industrial scale and do not have Cu-rich transitions. The samples were analyzed using glow discharge optical emission spectroscopy, scanning electron microscopy, X-ray diffraction, current–voltage-temperature, capacitance-voltage, external quantum efficiency, transmission/reflection, and photoluminescence. It was concluded that in spite of differences in the texturing, morphology and Ga gradient, the electrical performance of the two types of samples is quite similar as demonstrated by the similar J–V behavior, quantum spectral response, and the estimated recombination losses.