电气技术  2020, Vol. 21 Issue (3): 11-15    DOI:
研究与开发 |
基于经验模态分解法优化支持向量机模型的日前风电功率组合预测
夏书悦, 董心怡
南京工程学院电力工程学院,南京 211167
Day-ahead wind power combination prediction based on empirical mode decomposition method to optimize support vector machine model
Xia Shuyue, Dong Xinyi
School of Electric Power Engineering, Nanjing Institute of Technology, Nanjing 211167
全文: PDF (1153 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 针对风电场日前风电出力预测问题,应用一种基于经验模态分解法优化支持向量机的算法的短期风电功率组合预测方法。首先采用经验模态分解法将历史风电功率数据分解为一系列相对平稳的分量序列,以减少不同特征信息间的相互影响,然后采用优化的支持向量机法对所分解的各分量序列分别建立预测模型,针对各分量自身特点选用不同的核函数和参数以取得单个分量的最佳预测精度,最后把各个分量的预测结果叠加,形成风电功率的最终预测值。算例表明,与其他单一预测方法相比,本文使用的组合算法预测精度更高。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
夏书悦
董心怡
关键词 经验模态分解支持向量机风电功率组合预测    
Abstract:In order to solve the problem of wind power output forecast in wind farm, a combined short-term wind power forecast method based on empirical mode decomposition and support vector machine (SVM) algorithm is applied. First empirical mode decomposition method is used to decompose wind power data sequence into a series of relatively stable component, in order to reduce the mutual influence between different characteristic information, and then the optimization of support vector machine method is adopted for the decomposition of each component of the sequence prediction model, respectively, for each component characteristics choose different kernel functions and parameters in order to obtain the best prediction accuracy of a single component. Finally, the prediction results of each component of superposition forms the projections wind power in the end. Numerical examples show that the combined algorithm is more accurate than other single forecasting methods.
Key wordsempirical mode decomposition    support vector machine (SVM)    wind power    combination forecast   
收稿日期: 2019-09-02      出版日期: 2020-03-20
基金资助:南京工程学院大学生科技创新基金研究生训练项目(TB20191647);南京工程学院大学生科技创新基金项目(TB201904009)
作者简介: 夏书悦(1996-),女,江苏省扬州市人,硕士研究生,主要从事新能源并网运行与控制的研究工作。
引用本文:   
夏书悦, 董心怡. 基于经验模态分解法优化支持向量机模型的日前风电功率组合预测[J]. 电气技术, 2020, 21(3): 11-15. Xia Shuyue, Dong Xinyi. Day-ahead wind power combination prediction based on empirical mode decomposition method to optimize support vector machine model. Electrical Engineering, 2020, 21(3): 11-15.
链接本文:  
https://dqjs.cesmedia.cn/CN/Y2020/V21/I3/11