Prediction of Hourly Solar Radiation in Six Provinces in Turkey by Artificial Neural Networks
Yükleniyor...
Dosyalar
Tarih
2012
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
ASCE-AMER SOC CIVIL ENGINEERS
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
The purpose of this study is to apply the method of artificial neural networks (ANNs) to predict the hourly solar radiation of six selected provinces in Turkey. Six neurons-receiving input signals of latitude, longitude, altitude, day of the year, hour of the day, and mean hourly atmospheric air temperature-were used in the input layer of the network. One neuron producing a corresponding output signal of hourly solar radiation was utilized in the output layer of the network. Two different models have been analyzed in the ANNs for training and testing. The results obtained from both models were compared by using different neurons, mean squared error (MSE), coefficient of determination (R-2), and mean absolute error (MAE). According to the results, the MSE value of training data in Model II was better than Model I. DOI: 10.1061/(ASCE)EY.1943-7897.0000080. (C) 2012 American Society of Civil Engineers.
Açıklama
Anahtar Kelimeler
Artificial neural network, Back-propagation, Hourly solar radiation, Solar energy, Turkey
Kaynak
JOURNAL OF ENERGY ENGINEERING-ASCE
WoS Q Değeri
Q3
Scopus Q Değeri
Q2
Cilt
138
Sayı
4
