摘要
为提升大规模风电场风电功率超短期预测精度,减少由风电功率大幅度波动对电力系统带来的不利影响,提出一种基于原子稀疏分解(Atomic Sparse Decomposition,ASD)和混沌理论的风电功率超短期多步预测模型.首先,利用ASD良好的序列趋势跟踪特性,将风电功率时间序列分解成多个原子趋势分量和一个残差随机分量;其次分别利用自适应预测法和混沌理论对两分量进行超短期预测;最后,将两分量的预测结果叠加,得到最终的风电功率预测结果.选取我国东北某区域风电功率数据为例,算例结果表明,相较于传统预测模型,本文的预测方法能够有效地提升大规模风电场风电功率超短期预测精度.
In order to improve the accuracy of ultra-short-term wind power prediction,and reduce the adverse effects of wind power fluctuations on power systems,this paper presents an ultra-short-term multi-step wind power prediction model based on Atomic Sparse Decomposition(ASD)and chaos theory.Firstly,using the sequence trend tracking characteristics of ASD,the historical wind power time series is decomposed into multiple atomic trend components and one residual random component.Then,the two-part components are predicted by adaptive prediction method and chaos theory respectively.Finally,the two-part predicted values are superimposed.Taking the wind power data collected from a certain region in northeast China as an example,the simula-tion results show that,compared with the traditional prediction model,the proposed method of this paper can effectively improve the ultra-short-term prediction accuracy of wind power from large-scale wind farms.
作者
杨茂
刘慧宇
崔杨
YANG Mao;LIU Huiyu;CUI Yang(School of Electrical Engineering,Northeast Electric Power University,Jilin 132012,China)
出处
《昆明理工大学学报（自然科学版）》
CAS
北大核心
2019年第4期64-71,共8页
Journal of Kunming University of Science and Technology(Natural Science)
基金
国家重点研发计划项目(2018YFB0904200)
关键词
超短期风电功率预测
原子稀疏分解
混沌理论
预测精度
分频预测
ultra-short-term wind power prediction
atomic sparse decomposition
chaos theory
prediction ac-curacy
frequency division prediction
