Neural network for prediction solar radiation in Relizane region (Algeria) - Analysis study

The global solar radiation prediction is the most necessary part of the project and performance of solar energy applications. The objective of the present work is to predict global solar radiation (GSR) received on the horizontal surface using an artificial neural network (ANN). For the city (Relizane) in the west region of Algeria. The inputs used in the neural network are: time (h), day, month, year, temperature (k), relative humidity (%), pressure (mbar), wind speed (m/s), wind direction (°), and rainfall (kg/m2). The neural network-optimal model was trained and tested using 80 %, and 20 % of whole data, respectively. The best results were obtained with the structure 10-25-1 (10 inputs, 25 hidden, and 1 output neurons) presented an excellent agreement between the calculated and the experimental data during the test stage with a correlation coefficient of R = 0.9879, root means squared error of RMSE = 47.7192 (Wh/m2), mean absolute error MAE = 27.7397 (Wh/m2), and mean squared error MSE = 2.2771e+03(Wh/m2), considering a three-layer Feedforward neural network with Regularization Bayesienne (trainbr)  training algorithm, a hyperbolic tangent sigmoid and linear transfer function at the hidden and the output layer, respectively. The results demonstrate proper ANN’s predictions with a root mean square error (RMSE) of less than 0.50 (Wh/m2) and coefficient of correlation (R) higher than 0.98, which can be considered very acceptable. This model can be used for designing solar energy systems in the hottest regions.