基于变分模态分解和蝙蝠算法-相关向量机的短期风速区间预测

发布时间：2018-06-07 21:00

本文选题：风电 + 风速预测　；参考：《电力自动化设备》2017年01期

【摘要】：现有的风速预测方法大多是确定性的点预测,无法描述风速的随机性。针对该问题,建立基于变分模态分解(VMD)和蝙蝠算法-相关向量机(BA-RVM)的短期风速区间预测模型。对原始风速序列进行变分模态分解获得多个子序列;采用样本熵(SE)算法对子序列进行重组得到3类具有典型特性的分量;对各分量采用相关向量机算法分别建立预测模型。为进一步提高预测精度、缩小区间范围,引入蝙蝠算法(BA)对预测模型进行参数优化。将各分量的预测结果进行叠加求和得到一定置信水平下总体的区间预测结果。实际算例结果表明,与现有方法相比,所提区间预测方法的预测精度和区间覆盖率更高,区间宽度更窄。
[Abstract]:Most of the existing wind speed prediction methods are deterministic point prediction, which can not describe the randomness of wind speed. To solve this problem, a short-term wind speed interval prediction model based on variational mode decomposition (VMD) and bat algorithm-correlation vector machine (BA-RVM) is established. The original wind speed series is decomposed by variational mode decomposition to obtain multiple sub-sequences; the sample entropy SE) algorithm is used to recombine the sub-sequences to obtain three kinds of components with typical characteristics; the correlation vector machine algorithm is used to establish prediction models for each component. In order to further improve the prediction accuracy and reduce the range of the interval, the bat algorithm was introduced to optimize the parameters of the prediction model. The prediction results of each component are superimposed to obtain the interval prediction results of the population at certain confidence level. The results of practical examples show that, compared with the existing methods, the prediction accuracy and interval coverage of the proposed interval prediction methods are higher and the interval width is narrower.
【作者单位】：河海大学能源与电气学院;阿尔斯通电网技术中心有限公司;GE
【基金】：国家自然科学基金资助项目(51107032;61104045;51277052) 国家高技术研究发展计划(863计划)资助项目(2013AA050601)~~
【分类号】：TM614

【相似文献】