Solar Irradiance Prediction Using Bagging Decision Tree-Based Machine Learning

Abstract

Solar energy is one of the most widely used renewable energy sources to generate electricity. However, the amount of solar radiation reaching the earth's surface is variable, creating uncertainty in the output of electrical power generation systems that use this source. Therefore, solar irradiance prediction becomes a critical process in planning. This study presents a short-term prediction of solar irradiance using bagging decision tree-based machine learning. As the inputs of the proposed method, air temperature, hour, day, month, and previous solar irradiance values were determined. The performance of the proposed method is tested on the measured data. The R2 and RMSE values are 0.87 and 91.282, respectively, according to the results obtained. As a result, it has been revealed that the varying solar irradiance can be predicted with acceptable differences with this method.

Promoting Wind Energy by Robust Wind Speed Forecasting Using Machine Learning Algorithms Optimization

“…However, the graph shows that DT performance is low compared to others. That is because the deviation in tree structures variance emerges as the negative side of the method 69) . DT generally tends to have low bias and high variance 70) .…”