摘要
由于风电功率时间序列的非线性非平稳性特征,将一种基于集合经验模态分解(EEMD)和相关向量机(RVM)的预测模型引入到风电功率实时预测中。首先对风电功率时间序列采用集合经验模态分解,降低序列的非平稳性;其次对各子序列建立相关向量机预测模型;最后将得到的各子序列预测结果叠加就得到最终的功率预测值。利用该方法对吉林省某风电场进行功率预测,研究表明,该文所提出的预测模型能有效地提高预测精度,对工程有较高的利用价值。
According to the wind power of the non-linear and non-stationary characteristics, a based on ensemble empirical mode decomposition (EEMD) and relevance vector machine (RVM) prediction model is introduced into the wind power real-time prediction. At first, ensemble empirical mode decomposition and reduction sequence of nonstationary was applied to the wind power; second of every sub series to establish the relevance vector machine prediction model; at last, each sub sequence of the prediction stack result to get the power of the final prediction value. Using this method to predict the power of a wind farm in Jilin Province, the research showed that the proposed model can effectively improve the prediction accuracy, and has a high utilization value.
出处
《太阳能学报》
EI
CAS
CSCD
北大核心
2016年第5期1093-1099,共7页
Acta Energiae Solaris Sinica
基金
国家重点基础研究发展(973)计划(2013CB228201)
国家自然科学基金(51307017)
吉林省产业技术研究与开发专项(2014Y124)
国家留学基金(201507790001)
关键词
风电功率
功率预测
集合经验模态分解
相关向量机
wind power
power prediction
ensemble empirical mode decomposition
correlation vector machine