Assessing the potential of support vector machine for estimating daily solar radiation using sunshine duration | |
Li Guo-Sheng | |
2013 | |
关键词 | Support vector machines Estimation Mean square error Meteorology Models Solar radiation Sun |
英文摘要 | Estimation of solar radiation from sunshine duration offers an important alternative in the absence of measured solar radiation. However, due to the dynamic nature of atmosphere, accurate estimation of daily solar radiation has been being a challenging task. This paper presents an application of Support vector machine (SVM) to estimation of daily solar radiation using sunshine duration. Seven SVM models using different input attributes and five empirical sunshine-based models are evaluated using meteorological data at three stations in Liaoning province in China. All the SVM models give good performances and significantly outperform the empirical models. The newly developed model, SVM1 using sunshine ratio as input attribute, is preferred due to its greater accuracy and simple input attribute. It performs better in winter, while highest root mean square error and relative root mean square error are obtained in summer. The season-dependent SVM model is superior to the fixed model in estimation of daily solar radiation for winter, while consideration of seasonal variation of the data sets cannot improve the results for spring, summer and autumn. Moreover, daily solar radiation could be well estimated by SVM1 using the data from nearby stations. The results indicate that the SVM method would be a promising alternative over the traditional approaches for estimation of daily solar radiation. 2013 Elsevier Ltd. All rights reserved. |
出处 | Energy Conversion and Management |
卷 | 75页:311-318 |
收录类别 | EI |
语种 | 英语 |
内容类型 | EI期刊论文 |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/31235] |
专题 | 地理科学与资源研究所_历年回溯文献 |
推荐引用方式 GB/T 7714 | Li Guo-Sheng. Assessing the potential of support vector machine for estimating daily solar radiation using sunshine duration. 2013. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论