提出基于递推最小二乘法和小波变换的逐日太阳辐射度预测模型,根据气象数据,对不同的气候条件按照相似的日类型进行分类;对不同的日类型,建立不同的预测模型。结果表明:在日类型基础上,建立的递推最小二乘法与小波变换模型具有较高预测精度,在日照较充足的晴天,其预测精度明显高于阴天及雨天的预测精度。 Based on the meteorological data, we classify different daily climatic conditions according to similar daily types. Different forecasting models are established for different day types. The results show that the recursive least squares method and the wavelet transform model established on the basis of the type of day have higher prediction accuracy, and the prediction accuracy is obviously higher than that of cloudy and rainy days when the sunshine is abundant.