Evaluation of Random Forest-Genetic Algorithm Hybrid Model in Estimating Daily Solar Radiation

Solar energy is the most important source of renewable energy, in other words, the main source of energy on Earth. Therefore, estimating the solar radiation parameter with high accuracy is very important. In this regard, in the present study, meteorological data of 3 meteorological stations of Ardabil province, including Meshginshahr, Germi, and Nir for a period of 2 years (2017-2018) on a daily scale were used. Then, the intensity of daily solar radiation in each of the mentioned stations was estimated using random forest and random forest methods-genetic algorithm. The meteorological variables used included minimum, maximum and average temperature, relative humidity, and wind speed, which in eight different combinations were considered as input data in the model calculations. The obtained results were compared with each other using statistical parameters and the best models were selected. By comparing the results, the models of Nir, Meshginshahr, and Germi stations were ranked from highest to lowest modeling accuracy, respectively; So that the GA-RF-V model in Nir station with the root mean square error of 0.346 MJ/m2d and Kling-Gupta efficiency of 0.687 with the least error was introduced as the best model in this study. Also, the results showed that the genetic algorithm has helped to increase the accuracy of all utilized models.