中国电机工程学报Issue(25)：33-40,8.
基于样本熵和极端学习机的超短期风电功率组合预测模型
Combined Model for Ultra Short-term Wind Power Prediction Based on Sample Entropy and Extreme Learning Machine
摘要
Abstract
An ultra short-term wind power combined prediction approach based on empirical mode decomposition (EMD)-sample entropy (SE) and extreme learning machine (ELM) was proposed. Firstly, the wind power time series was decomposed into a series of wind power subsequences with obvious differences in complex degree by using EMD-SE. Secondly, the prediction models of each subsequence were constructed with least squares support vector machine (LSSVM), extreme learning machine (ELM) and ELM improved by primal ridge regression (PRR-ELM), of which the parameters and the input vector dimensions were determined by cross validation and chaotic phase space theory to improve the forecasting accuracy of each prediction model. Finally, taking the actual collecting data of certain a wind farm for an example, the simulation results illustrate that ELM and PRR-ELM prediction model based on EMD-SE are much better than the combined LSSVM model based on EMD-SE on forecasting accuracy and training speed, and the prediction results of ELM are closer to the actual value, by which it is possible to achieve the online ultra short-term wind power combined prediction with higher precision.关键词
风电预测/样本熵/极端学习机/岭回归/支持向量机Key words
wind power prediction/sample entropy/extreme learning machine/ridge regression/support vector machine分类
信息技术与安全科学引用本文复制引用
张学清,梁军,张熙,张峰,张利,徐兵..基于样本熵和极端学习机的超短期风电功率组合预测模型[J].中国电机工程学报,2013,(25):33-40,8.基金项目
国家自然科学基金项目(51177091)；山东省自然科学基金项目(ZR2010EM055)。Projects Supported by National Natural Science Foundation of China (51177091) （51177091）
Projects Supported by Shandong Province Natural Science Foundation (ZR2010EM055) （ZR2010EM055）
