Abstract:
The first objective of this study is to estimate the potential of solar irradiance in Algeria using an artificial intelligence approach, namely, convolutional neural networks (CNNs). The second objective is to visualize the different solar components DNI, DHI, and GHI as spatial maps. Data from 267 locations for 2005–2022, obtained from the NREL database, subdivided into training and testing data are used to build the different forecasting models. Testing data are not used when training CNNs to provide an indication of the performance at unknown locations. CNN models with 9 input variables average temperature, relative humidity, sunshine duration, wind speed, precipitation, longitude, latitude, altitude, and month were used to estimate the monthly values of GHI, DNI, and DHI. Statistical error analysis is conducted using mean absolute error (MAE), Mean Absolute Percentage Error (MAPE), Mean Bias Error (MBE) and coefficient of determination R
2. This study shows that CNNs can be a better solution to estimate solar irradiance data. Seasonal solar mapping was developed in a GIS environment, representing locations and values of solar irradiance. These maps offer valuable insights into solar energy resources, aiding in the implementation of solar energy systems.
Publisher's Version