摘要
针对风速序列在时序上的间歇性、波动性等特征,提出一种基于集合经验模态分解方法和粒子群优化算法优化支持向量机的组合型短期风速预测方法。采用分解算法进行扩展集成,采用组合-合作型预测模型实现各分量的准确预测,再将其进行重构得到最终预测结果。通过对中国北方某风电场的风速数据进行实例验证,证明了该模型能克服单一预测模型预测精度不高的问题,并拥有较优的泛化性能。
Aiming at the intermittent and fluctuating characteristics of the wind speed sequence in time series,a method based on ensemble empirical mode decomposition and particle swarm optimization was proposed to optimize the support vector machine combined short-term wind speed forecasting method.The decomposition algorithm is used for extended integration,and the combined-cooperative forecasting model is used to achieve accurate forecasting of each component,and it is reconstructed to obtain the final forecasting result.Through the example verification of wind speed data from a wind farm in northern China,it is proved that the model can overcome the problem of low prediction accuracy of a single prediction model,and has better generalization performance.
作者
闫帆
李傲燃
YAN Fan;LI Aoran(Yunnan University,Kunming 650504,China)
出处
《黑龙江电力》
CAS
2023年第5期402-406,共5页
Heilongjiang Electric Power
关键词
风力发电
风速预测
集合经验模态分解
支持向量机
粒子群算法
wind power generation
wind speed prediction
ensemble empirical mode decomposition
support vector machine
particle swarm optimization