Monthly Solar Prediction Using Machine Learning: Diyala Governorate, Iraq as a Case Study

Abstract

Solar radiation constitutes the Earth’s primary energy source and is critical in regulating surface radiation equilibrium, vegetation photosynthesis, hydrological cycles, and extreme atmospheric. On the other hand, the depletion of global fossil fuel reserves mandates the power sector to adopt renewable energy-based sources, including photovoltaic and wind energy conversion systems. Therefore, the precise solar radiation prediction is imperative for climate research and the solar industry. This paper illustrates the use of two machine-learning approaches: random forest (RF) and support vector machine (SVM), to predict surface solar radiation in the Diyala governorate of Iraq for one step ahead, utilizing only lagged monthly time series data of the factor as input predictors. The findings were evaluated using three performance measures: coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The results showed that using 10 monthly lags time series as input predictors leads to the best prediction performance. Furthermore, in terms of the RMSE, the prediction performance of the RF algorithm was better than that of the SVM algorithm (RF's RMSE, MAE, and R2 were 181.398, 129.522, and 0.979, while for SVM were 240.149, 184.802, and 0.978, respectively).