Daily UV radiation modeling with the usage of statistical correlations and artificial neural networks

Leal, S.S.; Tiba, Chigueru; Piacentini, R. D.

doi:10.1016/j.renene.2011.05.007

Cited by 27 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ANN is one of the important topics of machine learning. It is also used in many applications due to its multidisciplinary nature. 23,24 The development of new ANN models in scientific analysis processes has now gained a continuity.…”

Section: Methods Usedmentioning

confidence: 99%

Prediction of the effect of temperature on electric power in photovoltaic thermal systems based on natural zeolite plates

Metlek¹,

Kandilli

Kayaalp

2021

Intl J of Energy Research

View full text Add to dashboard Cite

Summary The present study aims to predict the effect of the panel temperature on the electrical power obtained by the photovoltaic thermal system (PVT) based on natural zeolite plates. It was carried out using the long short‐term memory (LSTM) and multilayer feed forward (MLF) algorithms, which are popular regression‐based deep learning methods. Models have been developed that can predict the effect of temperature on electrical power by using the regression data obtained from experimental measurements on the PVT system integrated with natural zeolite plates. In the study, a polycrystalline PVT panel was chosen, in the designed models, temperature, solar radiation, and photovoltaic panel temperature values were evaluated as input, and the amount of power to be produced as output. Mean absolute error, root mean square error (RMSE), mean absolute percentage error (MAPE), and R2 functions were used for the prediction results of LSTM and MLF models designed with determined optimum hyperparameters. MAPE and R2 values for long short‐term memory (LSTM) and MLF algorithms were determined as 0.100 and 0.996, as well as 0.131 and 0.923, respectively. As can be understood from these values, the effect of the designed temperature on the PVT panel can be calculated with a very small margin of error with the LSTM algorithm.

show abstract

Section: Methods Usedmentioning

confidence: 99%

Prediction of the effect of temperature on electric power in photovoltaic thermal systems based on natural zeolite plates

Metlek¹,

Kandilli

Kayaalp

2021

Intl J of Energy Research

View full text Add to dashboard Cite

show abstract

“…Dentre os tipos de redes neurais existentes, a Perceptron de Multicamadas (MLP) tem sido a mais utilizada na estimativa de dados de radiação solar (Barbero et al, 2006;Leal et al, 2011;Jacovides et al, 2015). A MLP é composta pelas seguintes estruturas: camadas de neurônios artificiais, cada uma responsável pela recepção dos sinais (dados de entrada), análise dos sinais (camadas ocultas) e saída dos dados estimados (camada de saída); um algoritmo de aprendizado, correspondente a um conjunto de regras definidas para resolver falhas no aprendizado e minimizar os erros; e uma função de ativação, que define a influência do algoritmo sobre a ativação dos neurônios (Haykin, 1998).…”

Section: Técnicas De Aprendizado De Máquinasunclassified

“…Contudo, poucos trabalhos avaliaram o uso das TAM na estimativa da UV solar, a grande maioria com foco na partição diária e utilizando as RNA (Barbero et al, 2006;Leal et al, 2011;Jacovides et al, 2015). Em tais trabalhos, a RNA apresentou o mesmo nível de acurácia dos modelos empíricos quando são utilizadas a R G , o índice de transmissividade atmosférica K T e a massa óptica relativa do ar como variáveis de entrada.…”

Section: Introductionunclassified

Comparação de Métodos de Estimativa da Radiação Solar Ultravioleta Horária: Modelos Empíricos, Redes Neurais Artificiais e Máquina de Vetores de Suporte

Teramoto

Santos

Escobedo

et al. 2020

Rev. bras. meteorol.

View full text Add to dashboard Cite

Resumo No presente trabalho, a comparação de três dos principais métodos de estimativa da radiação solar foi realizada: modelos empíricos, Redes Neurais Artificiais (RNA) e Máquina de Vetores de Suporte (SVM). Quatro modelos empíricos considerados clássicos foram calibrados e validados para a estimativa da radiação solar UV horária em Botucatu, Estado de São Paulo, Brasil. Mantendo os modelos empíricos como referências em relação a precisão e variáveis de entrada utilizadas, os desempenhos da RNA e da SVM foram avaliados. Por meio dos parâmetros estatísticos Erro Médio Padrão (MBE) e Erro Médio Absoluto (MAE) foi confirmada a superioridade da SVM em relação à RNA e aos modelos empíricos. Comparada à RNA, a SVM foi capaz de gerar melhores resultados utilizando um número menor de variáveis de entrada. Dentre todos os métodos de estimativa testados, a SVM utilizando o conjunto de variáveis de entrada {UV0, KT} é considerada a melhor alternativa devido ao pequeno número de variáveis de entrada utilizadas e pela relativa acurácia.

show abstract

“…Different measurements facilities are installed by Leal et al [21] for continuous daily UV and global radiation monitoring. They introduced statistical models to utilize daily global radiation to determine daily UV radiation.…”

Section: Introductionmentioning

confidence: 99%

Impact of UVB Solar Radiation on Ambient Temperature for Kuwait Desert Climate

Kadad¹,

Kandil²,

Alzanki³

2020

SGRE

View full text Add to dashboard Cite

This study examines the correlation between solar UVB and different weather parameters in Kuwait climate. To achieve that purpose, an experimental outdoor facility is designed and set up at the College of Technological Studies, Kuwait for regular monitoring of solar global radiation, UVB radiation and ambient temperature in Kuwait from beginning of January 1 st 2014 until the end of December 2019. Outcomes reveal that the change of solar UVB as well as global radiation through the whole day inaugurate the same behavior for the recorded data in clear day times. Statistical analysis is carried out to obtain a correlation linking UVB radiation and both ambient temperature and global solar radiation. Regression analysis of the current work shows that there is a solid correlation among UVB radiation and both ambient temperature and global solar radiation, especially for intermediate to small global solar radiation ranges. In addition, UV index is evaluated for various months at all day times. It is important to record that UV index with the maximum values is attained in May-August months through midday period. Also, UV index values do not surpass the accepted extreme value which is higher than 9 during any time of the study period.

show abstract

Daily UV radiation modeling with the usage of statistical correlations and artificial neural networks

Cited by 27 publications

References 7 publications

Prediction of the effect of temperature on electric power in photovoltaic thermal systems based on natural zeolite plates

Prediction of the effect of temperature on electric power in photovoltaic thermal systems based on natural zeolite plates

Comparação de Métodos de Estimativa da Radiação Solar Ultravioleta Horária: Modelos Empíricos, Redes Neurais Artificiais e Máquina de Vetores de Suporte

Impact of UVB Solar Radiation on Ambient Temperature for Kuwait Desert Climate

Contact Info

Product

Resources

About