相关性分析和GBDT组合的太阳辐射量预测算法

Prediction algorithm of solar radiation based on correlation analysis and GBDT combination

为准确预测太阳辐射量,提高太阳能利用效率,提出一种相关性分析和梯度提升决策树(gradient boosting decision tree,简称GBDT)组合的太阳辐射量预测算法.利用相关性分析选取预测算法的最优输入指标,使用数据矫正方法剔除粗大误差数据.将该文算法与传统算法的预测结果进行比较,结果表明该文组合预测算法具有更高的预测精度.

In order to accurately predict the solar radiation and improve the efficiency of solar energy utilization,an algorithm of solar radiation prediction based on the combination of correlation analysis and gradient boosting decision tree(GBDT)was proposed.The correlation analysis was used to select the optimal input index of the prediction algorithm,and the data correction method was used to eliminate the gross error data.Compared with the prediction results of the traditional algorithm,the results showed that the combined prediction algorithm had higher prediction accuracy.