Comparison of ANN, Regression Analysis, and ANFIS Models in Estimation of Global Solar Radiation for Different Climatological Locations
Küçük Resim Yok
Tarih
2018
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Elsevier Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In this study, the monthly mean daily global solar radiation (GSR) is modeled by artificial neural network (ANN), multilinear regression analysis (MLRA), and adaptive network-based fuzzy inference system (ANFIS) methods in the eight cities of Turkey. The results of three different models are compared and evaluated for these cities. The monthly means of daily sunshine duration, air temperature, relative humidity, wind speed, soil temperature, and GSR data of the cities are obtained from General Directorate of Meteorology and used to develop the models. Seven input parameters are determined using these meteorological data and some geographical equations. The root mean square error (RMSE), the mean absolute percentage error (MAPE), and the correlation coefficient (R) indicators are used to evaluate the performance of the models. For these performance indicators, the best values are obtained with ANN models. © 2018 Elsevier Inc. All rights reserved.
Açıklama
Anahtar Kelimeler
ANFIS, Artificial neural network, Estimation, Multilinear regression analysis, Solar radiation
Kaynak
Exergetic, Energetic and Environmental Dimensions
WoS Q Değeri
Scopus Q Değeri
N/A
