Use of radial basis functions for estimating monthly mean daily solar radiation

Mohandes, M.; Balghonaim, Adil; Kassas, Mahmoud; Rehman, Shafiqur; Halawani, T.O.

doi:10.1016/s0038-092x(99)00071-7

Cited by 165 publications

(66 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These results indicate that the model developed in this study is at least comparable to other models in this task. Model generated values for the hourly clearness index k t (using measured daily average cloudiness) were calculated using equation 37. Values of k t were also generated using the Aguiar and Collares-Pereira TAG algorithm [14].…”

Section: Hourly Irradiancementioning

confidence: 99%

A method for generating synthetic hourly solar radiation data for any location in the south west of Western Australia, in a world wide web page

2014

View full text Add to dashboard Cite

An algorithm was developed to generate synthetic hourly cloudiness data for any time of the year at any location in the south west region of Western Australia (WA). To enable the algorithm to be used for simulation of the power output of both tilted photovoltaic and concentrating solar power systems, a metric of cloudiness was defined which modifies the clear sky beam, diffuse and reflected solar transmittance. Seasonally and positionally adjusted values of daily cloudiness were generated by roughly mimicking the geographic pattern of annual rainfall in WA. Rather than longitude and latitude, distance along the coastline and distance inland from the coast were used as the positional coordinates. Hourly cloudiness data was generated from the daily values using a first order autoregression algorithm with time varying mean and standard deviation. Two years of measured hourly horizontal solar irradiance data from a network of 31 weather stations was used to calibrate the algorithm. The algorithm was simple enough to run inside a world wide web page and has the potential to be adapted to other regions with a similar pattern of declining inland rainfall.

show abstract

Section: Hourly Irradiancementioning

confidence: 99%

A method for generating synthetic hourly solar radiation data for any location in the south west of Western Australia, in a world wide web page

2014

View full text Add to dashboard Cite

show abstract

“…Also, prognostic and prediction models based on artificial intelligence techniques such as neural networks (NN) have been developed. These models can handle a large number of data, the contribution of these in the outcome can provide exact and adequate forecast (Krishnaiah, 2007;Adnan, 2004;Lopez, 2000;Mohandes et al, 2000).…”

Section: Angstrom-type Modelmentioning

confidence: 99%

Solar Radiation Models and Information for Renewable Energy Applications

Falayi¹,

Rabiu²

2012

Solar Radiation

View full text Add to dashboard Cite

“…Mohandes e cols. [44] repetem o estudo empregando uma RNA com topologia diferente: Radial Basis Function -RBF e observaram que esta topologia de RNA tambémé viável para obtenção de estimativas da energia solar incidente na superfície, mesmo quando a técnicaé comparada com estimativas produzidas por modelos clássicos de regressão.…”

Section: Aplicações Das Redes Neurais Artificiais Na Estimativa De Reunclassified

Aplicações de redes neurais e previsões de disponibilidade de recursos energéticos solares

Fiorin

Martins

Schuch

et al. 2011

Rev. Bras. Ensino Fís.

View full text Add to dashboard Cite

Este trabalho tem como objetivo discutir de forma sucinta a ferramenta matemática conhecida como redes neurais artificiais e algumas aplicações naárea de energias renováveis. Inicialmente, o trabalho descreve a relevância desta ferramenta estatística nas diversasáreas do conhecimento e, posteriormente, conceitua e descreve as principais configurações possíveis de uma rede neural artificial. Por fim, o trabalho demonstra a aplicação da ferramenta para o levantamento de disponibilidade de recursos de energia solar no Brasil a partir de dados de superfície coletados em estações da rede SONDA operada pelo Centro de Ciência do Sistema Terrestre do Instituto Nacional de Pesquisas Espaciais. Os resultados obtidos até o momento mostram que as redes neurais podem fornecer estimativas com a confiabilidade necessária para avaliação da disponibilidade de energia solar e com melhor desempenho que outras técnicas estatísticas utilizadas na literatura. Palavras-chave: energia solar, redes neurais artificiais, modelagem atmosférica, modelos de mesoescala.This work aims at discussing the artificial neural networks (ANN) and some applications in renewable energy assessment. First, the paper describes the statistical relevance of this tool in different areas of knowledge and the main ANN concepts and configurations. Finally, the paper presents and discusses the use of ANN for the solar energy assessment in Brazil by using data collected in SONDA sites operated by the Center for Earth System Science of the Brazilian Institute for Space Research. The results show that ANN can provide reliable estimates with better performance than other statistical tools.

show abstract

Use of radial basis functions for estimating monthly mean daily solar radiation

Cited by 165 publications

References 20 publications

A method for generating synthetic hourly solar radiation data for any location in the south west of Western Australia, in a world wide web page

A method for generating synthetic hourly solar radiation data for any location in the south west of Western Australia, in a world wide web page

Solar Radiation Models and Information for Renewable Energy Applications

Aplicações de redes neurais e previsões de disponibilidade de recursos energéticos solares

Contact Info

Product

Resources

About