An interdependent evolutionary machine learning model applied to global horizontal irradiance modeling

The most important input parameter in all solar power generation forecasting systems is solar radiation. Your estimation is necessary for the development of any photovoltaic system project. However, this estimate depends on expensive devices, namely pyranometers and pyrheliometers. Therefore, predicting such values through mathematical and computational models is an attractive approach where costs can be reduced. In particular, machine learning methods have been widely successfully applied to this task. The efficiency of a machine learning model depends on a suitable set of parameters. Evolutionary algorithms are helpful and widely used to optimize internal parameters and select the most relevant variables. In this context, machine learning models use evolutionary algorithms' search capability to improve forecasting performance. This work presents a study incorporating different evolutionary algorithms for parameter adjustment in machine learning models applied to solar radiation prediction. Two years of observation data from the Dar es Salaam weather station in Tanzania were used. The results show the presented framework's applicability to finding the best subset of variables, machine learning model and optimization algorithm combination. Although promising results have been obtained in the experiments, it should be clear that care must be taken to generalize the conclusions. The integration of machine learning model with optimization algorithms is limited to a defined data collection context, under specific local environmental conditions and only under data collection from a meteorological station.