AUTHOR=Belmahdi Brahim , Louzazni Mohamed , Akour Mohamed , Cotfas Daniel Tudor , Cotfas Petru Adrian , El Bouardi Abdelmajid 

TITLE=Long-Term Global Solar Radiation Prediction in 25 Cities in Morocco Using the FFNN-BP Method

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.733842

DOI=10.3389/fenrg.2021.733842

ISSN=2296-598X

ABSTRACT=This paper presents different combinations of inputs parameters based on an intelligent technique, using neural networks to predict daily Global Solar Radiation (GSR) for twenty-five Moroccan cities. The collected measured data is available for 365 days at twenty-five stations around Morocco. Different input parameters are used, such as clearness index KT, day-number, day-length, minimal temperature Tmin, maximal temperature Tmax, average temperature Taverage, difference temperature ∆T, ratio temperature T-Ratio, average humidity RH, Top Outside Atmosphere radiation TOA, average wind speed, altitude, longitude, latitude and solar declination. A different combination was employed to predict daily GSR for the considered locations, in order to find the most adequate input parameter that can be used in the prediction’s procedure. Several statistical metrics are applied to evaluate the performance of the obtained results, such as: Coefficients of determination R², Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Normalized Root Mean Square Error (NRMSE), Mean Bias Error (MBE), Test Statistic (TS), linear regression coefficients (the slope ‘a’ and the constant ‘b’) and Standard Deviation (σ). It is found that using input parameters in the Artificial Neural Network ANN model, gives good accurate results, obtaining the lower value of statistical metric. The results showed the best input of twenty five locations, 12 inputs for Er-Rachidia, Marrakech, Medilt, Taza, Oujda,  Nador, Tetouan, Tanger, Al-Auin, Dakhla, Settat, and Safi, 7 inputs for Fes, Ifrane, Beni-Mellal, and Meknes,6 inputs for Agadir and Rabat, 5 inputs for Sidi Ifni, Essaouira, Casablanca and Kenitra, 4 inputs for Ouarzazate, Lareche and Al-Hoceima, This technique could be used to predict other parameters for locations where measurement instrumentation is missed or is costly to obtain.