An ensemble learning model of multi-objective optimization for solar radiationFeng Jiang1, Jiawei Yang11Zhongnan University of Economics and Law, Wuhan 430073, Chinafjiang78@163.comAbstract: In recent years, solar energy has attracted much attention as the most ideal clean energy. Accurate prediction of solar radiation is essential for efficient use of photovoltaic energy. In this paper, an ensemble learning model for multi-objective optimization, which objectives are horizontal and directional accuracy, is proposed. Firstly, the data of solar radiation are decomposed into a series of signal sets by singular spectrum analysis (SSA). Then, the least squares support vector machine (LSSVM) optimized by non-dominated sorting genetic algorithm (NSGAII) is used to predict each component signal. Clustering method is used to cluster the samples of each component signal. Finally, the NSGAII-LSSVM method is used to ensemble the sample results to get the final prediction value. Solar radiation data of Italy 2017 are used to verify the performance of the hybrid model. The result of this comparison with 8 benchmark models shows that the hybrid model has better performance and smaller error values than all other benchmark models. In conclusion, the proposed ensemble learning model of multi-objective optimization is considerably effective and contains high robustness for the solar radiation data forecast.Keywords: Solar radiation forecasting, Multi-objective optimization, Ensemble learning, Least square support vector regression1. IntroductionSolar energy has recently caught great attention in the world, because it has been considered as the most suitable clean energy, which is also proved by the considerable application of solar power...
