Papers by Victor Hugo Quej Chi
A B S T R A C T Daily solar radiation is an important variable in many models. In this paper, the... more A B S T R A C T Daily solar radiation is an important variable in many models. In this paper, the accuracy and performance of three soft computing techniques (i.e., adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN) and support vector machine (SVM) were assessed for predicting daily horizontal global solar radiation from measured meteorological variables in the Yucatán Peninsula, México. Model performance was assessed with statistical indicators such as root mean squared error (RMSE), mean absolute error (MAE) and coefficient of determination (R 2). The performance assessment indicates that the SVM technique with requirements of daily maximum and minimum air temperature, extraterrestrial solar radiation and rainfall has better performance than the other techniques and may be a promising alternative to the usual approaches for predicting solar radiation.
Prediction of daily global solar radiation by using day of the year is particularly attractive be... more Prediction of daily global solar radiation by using day of the year is particularly attractive because this parameter is not dependent on the input of meteorological parameters. In this study, four existing day of the year-based (DYB) models were evaluated and a new empirical DYB model was developed for estimating daily global solar radiation on a horizontal surface for six automatic weather stations of Yucat an Peninsula, Mexico. The performance of the models was assessed with root mean squared error (RMSE), mean bias error (MBE), mean percentage error (MPE), mean absolute percentage error (MAPE), mean absolute bias error (MABE) and coefficient of determination (R 2). The results show that the new proposed Gaussian DYB model estimates daily solar radiation better than other DYB models. Furthermore, a seasonal analysis shows that the model has good performance in all seasons, including in the rainy season. The results also suggest that the new model can be useful for highly variable climate conditions.
This paper evaluates the accuracy and applicability of thirteen empirical global solar radiation ... more This paper evaluates the accuracy and applicability of thirteen empirical global solar radiation models for warm subhumid regions that use daily meteorological data at six stations in Mexico (Yucatán Peninsula). One of the models investigated is a new empirical model developed for estimation of daily global solar radiation from a horizontal surface. The models were evaluated using root mean squared error (RMSE), mean bias error (MBE), mean percentage error (MPE), mean absolute percentage error (MAPE), mean absolute bias error (MABE) and coefficient of determination (R 2). Results show that the newly developed model performs best for all stations; models based on temperature, rainfall and air humidity performed better than models that used temperature data only. If only temperature data are available for estimation of global solar radiation, the Bristow and Campbell model had the best results. The new proposed model can be used in hydrologic and agricultural studies to estimate global solar radiation in warm subhumid regions when temperature, precipitation and humidity data are available.
Uploads
Papers by Victor Hugo Quej Chi