基于MKL方法的短期風(fēng)電功率預(yù)測研究
發(fā)布時(shí)間：2018-11-22 13:31
【摘要】：支持向量機(jī)(Support Vector Machine,SVM)等核學(xué)習(xí)方法是解決非線性問題的一種有效方法,在短期風(fēng)電功率預(yù)測中已有成功的應(yīng)用。多核學(xué)習(xí)(Multiple Kernel Learning,MKL)作為一種的新型核學(xué)習(xí)方法,通過核權(quán)值系數(shù)將具有不同特性的核函數(shù)進(jìn)行組合,其核權(quán)值系數(shù)使得核函數(shù)的選擇問題轉(zhuǎn)化為核權(quán)值系數(shù)的分布問題,且核權(quán)值系數(shù)的稀疏性能增強(qiáng)決策函數(shù)可解釋性,其不同核函數(shù)組合形成的再生希爾伯特空間使模型具有更強(qiáng)的泛化能力與魯棒性。為了進(jìn)一步提高短期風(fēng)電功率預(yù)測模型的性能,以MKL方法為主線,研究其在短期風(fēng)電功率直接預(yù)測與間接預(yù)測方面的應(yīng)用。本文的主要研究內(nèi)容如下:(1)分析了用于數(shù)據(jù)預(yù)處理的經(jīng)驗(yàn)?zāi)B(tài)分解方法(Empirical Mode Decomposition,EMD)和經(jīng)驗(yàn)小波變換方法(Empirical Wavelet Transform,EWT)的基本原理及其實(shí)現(xiàn)步驟,并通過ECG(Electrocardiograph,心電圖)標(biāo)準(zhǔn)數(shù)據(jù)集對其進(jìn)行對比分析,實(shí)驗(yàn)結(jié)果表明,EWT分解得到模態(tài)信號分量數(shù)量明顯少于EMD得到的模態(tài)信號分量數(shù)量且EMD分解得到的模態(tài)分量存在明顯的模態(tài)混疊現(xiàn)象。在SVM理論的基礎(chǔ)上,對基于半無限線性規(guī)劃的多核學(xué)習(xí)及MKL-wrapper算法和MKL-chunking算法進(jìn)行了深入研究,并簡要闡述了Simple MKL方法的基本原理及其具體實(shí)現(xiàn)步驟。(2)分析了某大型風(fēng)電場輸出功率不同季節(jié)中的季節(jié)周期性和時(shí)間連續(xù)性的特點(diǎn),并從不同季節(jié)中隨機(jī)選取四個(gè)具有不同特性測試周的風(fēng)電功率數(shù)據(jù)作為測試集;將自適應(yīng)分解預(yù)處理方法EWT與由MKL-wrapper、MKL-chunking、Simple MKL算法實(shí)現(xiàn)的MKL方法結(jié)合,形成一種新的組合預(yù)測方法,即EWT-MKL方法;將不同MKL方法應(yīng)用于不同季節(jié)的短期風(fēng)電功率直接預(yù)測實(shí)例中,在同等條件下,并與SVM方法進(jìn)行對比。實(shí)驗(yàn)結(jié)果表明,MKL預(yù)測模型的精度優(yōu)于SVM方法,而不同算法實(shí)現(xiàn)的EWT-MKL組合預(yù)測模型的效果最好,不同季節(jié)測試集中MKL模型的核參數(shù)及懲罰函數(shù)在取值范圍內(nèi)的隨機(jī)取值及其實(shí)驗(yàn)結(jié)果表明,MKL具有較強(qiáng)的泛化能力且其對參數(shù)的選擇具有較強(qiáng)的魯棒性。(3)分析了不同“風(fēng)速-功率”特性曲線求解方法對風(fēng)速-功率轉(zhuǎn)換精度的影響;將不同算法實(shí)現(xiàn)的MKL預(yù)測方法及EWT-MKL組合預(yù)測方法應(yīng)用于某風(fēng)電場平均風(fēng)速的短期預(yù)測;結(jié)合“風(fēng)速-功率”特性曲線實(shí)現(xiàn)短期風(fēng)電功率間接預(yù)測,并在同等條件下與小波支持向量機(jī)(Wavelet Support Vector Machines,WSVM)方法進(jìn)行對比。實(shí)驗(yàn)結(jié)果表明,在短期風(fēng)電功率間接預(yù)測中,不同算法實(shí)現(xiàn)的EWT-MKL組合預(yù)測模型的精度明顯高于MKL、SVM及WSVM等方法,而MKL預(yù)測模型的精度優(yōu)于SVM方法建立的預(yù)測模型。
[Abstract]:Support Vector Machine (Support Vector Machine,SVM) is an effective method to solve nonlinear problems and has been successfully applied in short-term wind power prediction. As a new kernel learning method, multi-kernel learning (Multiple Kernel Learning,MKL) combines kernel functions with different characteristics through kernel weight coefficients, and the kernel weight coefficients transform the selection of kernel functions into the distribution of kernel weight coefficients. The sparse property of the kernel weight coefficient enhances the interpretability of the decision function, and the reproducing Hilbert space formed by the combination of different kernel functions makes the model have stronger generalization ability and robustness. In order to further improve the performance of short-term wind power prediction model, the application of MKL method in direct and indirect prediction of short-term wind power is studied. The main contents of this paper are as follows: (1) the basic principle and implementation steps of empirical mode decomposition (Empirical Mode Decomposition,EMD) and empirical wavelet transform (Empirical Wavelet Transform,EWT) for data preprocessing are analyzed. The experimental results show that the number of modal signal components obtained by EWT decomposition is obviously less than that obtained by EMD, and the modal components obtained by EMD decomposition have obvious modal aliasing phenomenon. On the basis of SVM theory, the multi-core learning based on semi-infinite linear programming, MKL-wrapper algorithm and MKL-chunking algorithm are studied. The basic principle of Simple MKL method and its realization steps are briefly described. (2) the characteristics of seasonal periodicity and time continuity in different seasons of output power of a large wind farm are analyzed. Four wind power data with different characteristic test weeks were randomly selected from different seasons as the test set. Combining the adaptive decomposition preprocessing method (EWT) with the MKL method realized by MKL-wrapper,MKL-chunking,Simple MKL algorithm, a new combined prediction method, EWT-MKL method, is formed. The different MKL method is applied to the direct prediction of short-term wind power in different seasons. Under the same conditions, the method is compared with the SVM method. The experimental results show that the precision of MKL prediction model is better than that of SVM method, and the effect of EWT-MKL combination prediction model realized by different algorithms is the best. The random values of the kernel parameters and penalty functions of the MKL model in different season test sets are obtained in the range of values and the experimental results show that, MKL has strong generalization ability and strong robustness to parameter selection. (3) the influence of different "wind speed power" characteristic curve solving method on the precision of wind speed power conversion is analyzed. The MKL forecasting method and the EWT-MKL combination forecasting method realized by different algorithms are applied to the short-term prediction of the average wind speed of a wind farm. Combined with the characteristic curve of "wind speed and power", indirect prediction of short-term wind power is realized, and compared with wavelet support vector machine (Wavelet Support Vector Machines,WSVM) method under the same conditions. The experimental results show that the accuracy of EWT-MKL combination prediction model implemented by different algorithms is obviously higher than that of MKL,SVM and WSVM methods in indirect prediction of short-term wind power, while the accuracy of MKL prediction model is better than that of SVM method.
【學(xué)位授予單位】：蘭州交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TM614
[Abstract]:Support Vector Machine (Support Vector Machine,SVM) is an effective method to solve nonlinear problems and has been successfully applied in short-term wind power prediction. As a new kernel learning method, multi-kernel learning (Multiple Kernel Learning,MKL) combines kernel functions with different characteristics through kernel weight coefficients, and the kernel weight coefficients transform the selection of kernel functions into the distribution of kernel weight coefficients. The sparse property of the kernel weight coefficient enhances the interpretability of the decision function, and the reproducing Hilbert space formed by the combination of different kernel functions makes the model have stronger generalization ability and robustness. In order to further improve the performance of short-term wind power prediction model, the application of MKL method in direct and indirect prediction of short-term wind power is studied. The main contents of this paper are as follows: (1) the basic principle and implementation steps of empirical mode decomposition (Empirical Mode Decomposition,EMD) and empirical wavelet transform (Empirical Wavelet Transform,EWT) for data preprocessing are analyzed. The experimental results show that the number of modal signal components obtained by EWT decomposition is obviously less than that obtained by EMD, and the modal components obtained by EMD decomposition have obvious modal aliasing phenomenon. On the basis of SVM theory, the multi-core learning based on semi-infinite linear programming, MKL-wrapper algorithm and MKL-chunking algorithm are studied. The basic principle of Simple MKL method and its realization steps are briefly described. (2) the characteristics of seasonal periodicity and time continuity in different seasons of output power of a large wind farm are analyzed. Four wind power data with different characteristic test weeks were randomly selected from different seasons as the test set. Combining the adaptive decomposition preprocessing method (EWT) with the MKL method realized by MKL-wrapper,MKL-chunking,Simple MKL algorithm, a new combined prediction method, EWT-MKL method, is formed. The different MKL method is applied to the direct prediction of short-term wind power in different seasons. Under the same conditions, the method is compared with the SVM method. The experimental results show that the precision of MKL prediction model is better than that of SVM method, and the effect of EWT-MKL combination prediction model realized by different algorithms is the best. The random values of the kernel parameters and penalty functions of the MKL model in different season test sets are obtained in the range of values and the experimental results show that, MKL has strong generalization ability and strong robustness to parameter selection. (3) the influence of different "wind speed power" characteristic curve solving method on the precision of wind speed power conversion is analyzed. The MKL forecasting method and the EWT-MKL combination forecasting method realized by different algorithms are applied to the short-term prediction of the average wind speed of a wind farm. Combined with the characteristic curve of "wind speed and power", indirect prediction of short-term wind power is realized, and compared with wavelet support vector machine (Wavelet Support Vector Machines,WSVM) method under the same conditions. The experimental results show that the accuracy of EWT-MKL combination prediction model implemented by different algorithms is obviously higher than that of MKL,SVM and WSVM methods in indirect prediction of short-term wind power, while the accuracy of MKL prediction model is better than that of SVM method.
【學(xué)位授予單位】：蘭州交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TM614
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 祝文穎;馮志鵬;;基于改進(jìn)經(jīng)驗(yàn)小波變換的行星齒輪箱故障診斷[J];儀器儀表學(xué)報(bào);2016年10期
2 季峰;蔡興國;王超柱;;基于弱魯棒優(yōu)化的含風(fēng)電電力系統(tǒng)調(diào)度方法[J];中國電機(jī)工程學(xué)報(bào);2016年17期
3 錢政;裴巖;曹利宵;王婧怡;荊博;;風(fēng)電功率預(yù)測方法綜述[J];高電壓技術(shù);2016年04期
4 李沁雪;廖曉文;張清華;崔得龍;;基于EWT和多尺度熵的軸承特征提取及分類[J];軸承;2016年01期
5 黃南天;張書鑫;蔡國偉;徐殿國;;采用EWT和OCSVM的高壓斷路器機(jī)械故障診斷[J];儀器儀表學(xué)報(bào);2015年12期
6 楊錫運(yùn);關(guān)文淵;劉玉奇;肖運(yùn)啟;;基于粒子群優(yōu)化的核極限學(xué)習(xí)機(jī)模型的風(fēng)電功率區(qū)間預(yù)測方法[J];中國電機(jī)工程學(xué)報(bào);2015年S1期
7 崔嘉;楊俊友;邢作霞;李媛;王海鑫;馬洪斌;;基于單機(jī)最優(yōu)功率曲線擬合的多場景風(fēng)電功率預(yù)測方法[J];電力系統(tǒng)自動化;2015年16期
8 楊茂;齊s，
本文編號：2349514
本文鏈接：http://sikaile.net/kejilunwen/dianlidianqilunwen/2349514.html
最近更新
教材專著
