Wind power short-term prediction based on principal component analysis of NWP of multiple locations

被引：0

作者：

Beijing Information Science and Technology University, Beijing ^{[1
]}

100192, China

不详 ^{[2
]}

100081, China

机构：

来源：

Diangong Jishu Xuebao | / 5卷 / 79-84期

关键词：

Weather forecasting - Wind farm - Electric utilities - Cluster analysis - Location - Electric power generation - Electric power system interconnection;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Numerical weather prediction (NWP) plays an important role in the accuracy of the short-term wind power prediction models. Considering NWP information of multiple locations around a wind farm, this paper introduces a method based on the cluster analysis and the principal component analysis to study the short-term prediction of the wind power generating capacity. The sample in the historical data closest to the NWP of the forecast day is extracted by the clustering analysis. Then the principal component analysis of the sample information is proceeded to obtain the parameters which reflects the characteristics of the wind farm. Simulation is performed consideringthe wind power generation of Yilan wind farm. The results show that the method is effective and its precision improves 4. 65% than the prediction model based on NWP of single location. ©, 2015, Chinese Machine Press. All right reserved.

引用