Evaluation of Artificial Neural Networks with Satellite Data Inputs for Daily, Monthly, and Yearly Solar Irradiation Prediction for Pakistan

Solar irradiation is the most critical parameter to consider when designing solar energy systems. The high cost and difficulty of measuring makes it impractical in every location. This study’s primary objective was develop an artificial neural network (ANN) model for global horizontal (GHI) prediction using satellite data inputs. Three types ANN, namely, feed forward (FFNN), cascaded (CFNN), Elman (EMNN), were tested. findings revealed that altitude, relative humidity, GHI are effective parameters, as they present all best-performing models. best daily FFNN, which decreased MAPE, RMSE, MBE by 25.4%, 0.11 kWh/m2/d, 0.01 kWh/m2/d. FFNN values 7.83%, 0.49 EMNN performed monthly annual prediction, reducing 50.62%, 0.13 while reduction yearly 91.6%, 0.2 3.36%, 0.16 0.47%, 0.18 0.004