当前位置：
X-MOL 学术
›
Energy Convers. Manag.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Improving solar radiation estimation in China based on regional optimal combination of meteorological factors with machine learning methods
Energy Conversion and Management ( IF 9.9 ) Pub Date : 2020-09-01 , DOI: 10.1016/j.enconman.2020.113111 Chuan He , Jiandong Liu , Fang Xu , Teng Zhang , Shang Chen , Zhe Sun , Wenhui Zheng , Runhong Wang , Liang He , Hao Feng , Qiang Yu , Jianqiang He
Energy Conversion and Management ( IF 9.9 ) Pub Date : 2020-09-01 , DOI: 10.1016/j.enconman.2020.113111 Chuan He , Jiandong Liu , Fang Xu , Teng Zhang , Shang Chen , Zhe Sun , Wenhui Zheng , Runhong Wang , Liang He , Hao Feng , Qiang Yu , Jianqiang He
Abstract The values of global solar radiation are important fundamental data for potential evapotranspiration estimation, solar energy utilization, climate change study, crop growth model, and etc. This research tried to explore the optimal combination of input meteorological factors and the machine learning methods for the estimation of daily solar radiation under different climatic conditions so as to improve the estimation accuracy. Based on the correlation between meteorological factors, different meteorological factor input combinations were established and the support vector machine method was used to estimate global solar radiation at 80 weather stations in four climatic regions of China mainland. The results showed that, the optimal combinations of input meteorological factors were different in the four different climatic zones in China mainland. Three meteorological factors of sunshine hours, extraterrestrial radiation, and air temperature had greater impacts on the solar radiation estimation. Adding the factor of precipitation could obviously improve the estimation accuracy in humid regions, but not remarkably in arid regions. Wind speed had very little influence on solar radiation estimation. The accuracies of machine learning methods were better than the Angstrom-Prescott formula and the multiple linear regression method. Among them, support vector machine and extreme learning machine were more appropriate. In some sites, the root mean square error of support vector machine method was even 20% less than that of the Angstrom-Prescott formula. In general, reasonable division of the areas and establishment of appropriate input combinations of meteorological factors according to the climatic conditions, combined with machine learning methods, can effectively improve the accuracy of solar radiation estimation.
更新日期：2020-09-01
京公网安备 11010802027423号