Hourly Solar Radiation Forecast Based on k-NN Nonparametric Regression Model. Applied Mechanics and Materials.
Hourly Solar Radiation Forecast Based on k-NN Nonparametric Regression Model. Applied Mechanics and Materials.
复制标题
基于 k-NN 非参数回归模型的每小时太阳辐射预测。
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Xiaoying Wang
中科院分区：
文献类型：
--
作者：
Mengqin Yang;Xiaoying Wang
太阳辐射具有非常突出的非线性特征，难以准确预测，因此本文提出了基于k-NN模型的四种主要模型，以时间、日照时数、温度、风速和湿度作为输入数据，用于每小时的太阳辐射预测。西宁地区太阳辐射瞬时值预测模型是通过青海大学的实验建立的。优化模型的准确率平均达到88.7%，在允许绝对百分比误差低于20%的前提下最高可达97.01%。
It is hard to accurately predict solar radiation due to its very prominent nonlinear feature,so four major models based on the k-NN model, which have time, sunshine hours, temperature,wind speed and humidity as input data, are presented in the paper for hourly solar radiationforecasting. The models forecasting instantaneous solar radiation values in the Xining region have been created through experiments carried out in Qinghai University. The accuracy of the optimum model is up to 88.7% on average and 97.01% at most on the premise and the allowed absolute percentage error is lower than 20%.