【摘要】：支持向量機(jī)預(yù)測模型雖然已被證實為一類優(yōu)于神經(jīng)網(wǎng)絡(luò)等其他智能算法模型的新興預(yù)測技術(shù)，但其本身依舊不夠完美，仍然存在尚需改進(jìn)的地方。 本文選取了支持向量機(jī)家族中的最小二乘支持向量機(jī)預(yù)測模型進(jìn)行研究，并發(fā)現(xiàn)在使用該模型進(jìn)行訓(xùn)練時，由于其對訓(xùn)練樣本的各個輸入向量的懲罰度是一樣的，即在訓(xùn)練過程中對所有輸入點(diǎn)都等同看待，因此，一旦在訓(xùn)練樣本集中出現(xiàn)離群點(diǎn)時，該點(diǎn)就會對預(yù)測模型產(chǎn)生一定的不良影響。這樣一來，勢必會降低系統(tǒng)的魯棒性，引起過學(xué)習(xí)，降低了預(yù)測模型的推廣能力和預(yù)測效果。 本文關(guān)注了此項問題，，嘗試對原模型進(jìn)行改進(jìn)，從而使得改進(jìn)后的預(yù)測模型能夠很好地克服上述理論缺陷，優(yōu)化預(yù)測過程與結(jié)果，達(dá)到管理科學(xué)理論創(chuàng)新的目的。 為了達(dá)到上述目的，作者在經(jīng)過了大量的研究與參考后，運(yùn)用模糊數(shù)學(xué)中有關(guān)隸屬度問題的相關(guān)理論和方法與原預(yù)測模型相結(jié)合，建立了一套新的預(yù)測模型。為了考察該模型是否能達(dá)到對原預(yù)測模型的改進(jìn)效果，并使得預(yù)測結(jié)果更佳，文章選取了美國PJM電力市場在2012年內(nèi)的一些有關(guān)日前交易的負(fù)荷與邊際電價數(shù)據(jù)進(jìn)行預(yù)測。首先，運(yùn)用新模型對多個測試日的邊際電價進(jìn)行預(yù)測，通過Matlab軟件加以實現(xiàn)，并得出了多個測試日的相關(guān)預(yù)測結(jié)果。之后，又運(yùn)用原模型在相同條件下對相同日期的邊際電價進(jìn)行預(yù)測并得出預(yù)測結(jié)果。最后，通過將兩種模型在多個測試日的預(yù)測值與真實值之間的誤差進(jìn)行比較，發(fā)現(xiàn)新模型的預(yù)測誤差明顯低于原模型。這一點(diǎn)證實了新模型確實起到了對原模型明顯的改進(jìn)效果，所得出的預(yù)測結(jié)果對未來發(fā)電企業(yè)的管理者作進(jìn)一步分析與決策更加具有參考意義。另外，改進(jìn)后的新模型在算法實現(xiàn)方面較之改進(jìn)前的原模型并沒有明顯增加計算的復(fù)雜度，這又從另一個方面證實了該改進(jìn)方案的有效性。 綜上所述，本文通過改進(jìn)而得到的新模型可以被廣泛推廣，而且范圍不僅局限在電價預(yù)測領(lǐng)域之內(nèi)。這對于管理科學(xué)理論創(chuàng)新與應(yīng)用等領(lǐng)域的研究都具有一定的貢獻(xiàn)與啟發(fā)意義。
[Abstract]:Support vector machine (SVM) prediction model has been proved to be a kind of new prediction technology which is superior to other intelligent algorithm models such as neural network, but it itself is still not perfect, and there are still some problems to be improved. In this paper, the prediction model of least squares support vector machine (LS-SVM) in the family of support vector machines (SVM) is selected, and it is found that the penalty degree of each input vector of the training sample is the same when the model is used for training. That is, all input points are treated equally in the training process, so once the outliers appear in the training sample set, the outliers will have a certain adverse effect on the prediction model. In this way, the robustness of the system will be reduced, and the overlearning will be caused, and the generalization ability and prediction effect of the prediction model will be reduced. This paper focuses on this problem and attempts to improve the original model, so that the improved prediction model can overcome the above theoretical defects, optimize the prediction process and results, and achieve the purpose of theoretical innovation in management science. In order to achieve the above purpose, after a lot of research and reference, the author combines the theory and method of membership degree in fuzzy mathematics with the original prediction model, and establishes a new prediction model. In order to investigate whether the model can improve the original forecasting model and make the forecast result better, this paper selects some data of pre-day trading load and marginal electricity price of PJM electricity market in the United States in 2012 to forecast. Firstly, the new model is used to predict the marginal electricity price of multiple test days, which is realized by Matlab software, and the related prediction results of multiple test days are obtained. After that, the original model is used to predict the marginal electricity price of the same date under the same conditions and the prediction results are obtained. Finally, it is found that the prediction error of the new model is obviously lower than that of the original model by comparing the errors between the predicted values and the real values of the two models on multiple test days. This proves that the new model does improve the original model obviously, and the predicted results are more useful for the future power generation enterprise managers to make further analysis and decision making. In addition, the algorithm implementation of the improved new model does not significantly increase the computational complexity compared with the original model, which proves the effectiveness of the improved scheme from another aspect. To sum up, the new model can be extended widely, and the scope is not only limited to the field of electricity price prediction. It has a certain contribution and enlightening significance to the research of management science theory innovation and application.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：F224;F416.61

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 黃日星,康重慶,夏清;電力市場中的邊際電價預(yù)測[J];電力系統(tǒng)自動化;2000年22期

2 楊莉,邱家駒,江道灼;基于BP網(wǎng)絡(luò)的下一交易日無約束市場清算價格預(yù)測模型[J];電力系統(tǒng)自動化;2001年19期

3 張顯;王錫凡;;短期電價預(yù)測綜述[J];電力系統(tǒng)自動化;2006年03期

4 蘇娟;杜松懷;李才華;;基于多因素小波分析的神經(jīng)網(wǎng)絡(luò)短期現(xiàn)貨電價預(yù)測方法[J];電力自動化設(shè)備;2007年11期

5 陳建華,周浩;基于小腦模型關(guān)節(jié)控制器神經(jīng)網(wǎng)絡(luò)的短期電價預(yù)測[J];電網(wǎng)技術(shù);2003年08期

6 吳宏曉,侯志儉;基于免疫支持向量機(jī)方法的電力系統(tǒng)短期負(fù)荷預(yù)測[J];電網(wǎng)技術(shù);2004年23期

7 楊延西,劉丁;基于小波變換和最小二乘支持向量機(jī)的短期電力負(fù)荷預(yù)測[J];電網(wǎng)技術(shù);2005年13期

8 程曉鑫;周渝慧;;基于灰色改進(jìn)模型的電價預(yù)測[J];華北電力大學(xué)學(xué)報;2006年01期

9 蘇娟;杜松懷;;GM(1,2)短期現(xiàn)貨電價灰色預(yù)測模型[J];繼電器;2006年01期

10 陳思杰;周浩;;電力市場電價預(yù)測方法綜述[J];繼電器;2006年11期

相關(guān)博士學(xué)位論文 前1條

1 馮業(yè)偉;基于支持向量機(jī)和移動Agent技術(shù)的銀行風(fēng)險早期預(yù)警系統(tǒng)研究[D];中國海洋大學(xué);2011年

相關(guān)碩士學(xué)位論文 前1條

1 梁懷翔;支持向量機(jī)遙感圖像分類的研究[D];長安大學(xué);2011年

本文編號：2159612