發(fā)布時(shí)間：2018-03-01 18:25

  本文關(guān)鍵詞： 風(fēng)電功率預(yù)測(cè) 經(jīng)驗(yàn)?zāi)Ｊ椒纸?相空間重構(gòu) 支持向量機(jī) 元學(xué)習(xí)組合預(yù)測(cè)　出處：《湖南大學(xué)》2014年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隨著大規(guī)模風(fēng)電接入電網(wǎng)，風(fēng)電功率的波動(dòng)性和間歇性給電力系統(tǒng)安全穩(wěn)定運(yùn)行帶來(lái)了嚴(yán)峻的挑戰(zhàn)。風(fēng)電功率預(yù)測(cè)是解決大規(guī)模風(fēng)電接入電網(wǎng)的關(guān)鍵技術(shù)之一，能夠?yàn)殡娏ο到y(tǒng)調(diào)度控制提供技術(shù)支持。目前國(guó)內(nèi)針對(duì)風(fēng)電功率預(yù)測(cè)方法的研究取得了一定的成果但不夠深入，預(yù)測(cè)系統(tǒng)的開(kāi)發(fā)剛剛起步，缺乏規(guī)范和實(shí)踐經(jīng)驗(yàn)。因此，對(duì)風(fēng)電功率預(yù)測(cè)方法研究具有重要的意義。 本文以某風(fēng)電場(chǎng)為研究對(duì)象，對(duì)風(fēng)電場(chǎng)風(fēng)速分布風(fēng)電功率時(shí)間特征展開(kāi)了系統(tǒng)的研究，以探求更高精度的風(fēng)電功率預(yù)測(cè)方法。同時(shí)，，根據(jù)需求分析研發(fā)了風(fēng)電功率預(yù)測(cè)系統(tǒng)。主要內(nèi)容如下： 首先，以某風(fēng)電場(chǎng)為對(duì)象，對(duì)風(fēng)速功率特性進(jìn)行了系統(tǒng)的研究。結(jié)果表明：風(fēng)速的概率分布呈現(xiàn)威布爾分布特征；風(fēng)電功率具有隨機(jī)性波動(dòng)性和混沌性，隨著時(shí)間尺度的降低風(fēng)電功率的波動(dòng)性減弱。 然后，提出了一種以經(jīng)驗(yàn)?zāi)Ｊ椒纸猓‥mpirical Mode Decomposition,EMD）和相空間重構(gòu)為核心的風(fēng)電功率預(yù)測(cè)方法，將分解后的本征模函數(shù)（IntrinsicModel Function, IMF）分量和剩余分量進(jìn)行相空間重構(gòu)，將重構(gòu)序列輸入支持向量機(jī)（Support Vector Machine,SVM）模型預(yù)測(cè)風(fēng)電功率。結(jié)果表明，經(jīng)過(guò)EMD分解降低了建模復(fù)雜程度，相空間重構(gòu)能夠降低偏差較大分量對(duì)預(yù)測(cè)結(jié)果的影響，提高了預(yù)測(cè)的精確度。 其次，提出了基于元學(xué)習(xí)的風(fēng)電功率非線性組合預(yù)測(cè)模型。以灰色模型時(shí)間序列模型線性回歸模型和神經(jīng)網(wǎng)絡(luò)模型預(yù)測(cè)結(jié)果和預(yù)測(cè)序列的特征屬性作為元預(yù)測(cè)器的輸入，從而發(fā)現(xiàn)并糾正基預(yù)測(cè)器的系統(tǒng)偏差。在元預(yù)測(cè)器中，采用門(mén)控網(wǎng)絡(luò)函數(shù)確定各基預(yù)測(cè)器權(quán)重，保證了權(quán)重的時(shí)變性和非負(fù)性。將該算法應(yīng)用于風(fēng)電功率預(yù)測(cè)，預(yù)測(cè)結(jié)果表明：該算法預(yù)測(cè)精度高于單一預(yù)測(cè)算法和常用的組合預(yù)測(cè)算法。 最后，根據(jù)需求分析開(kāi)發(fā)了一套風(fēng)電功率預(yù)測(cè)系統(tǒng)，實(shí)現(xiàn)了對(duì)風(fēng)電功率的短期預(yù)測(cè)。通過(guò)某風(fēng)電場(chǎng)實(shí)測(cè)數(shù)據(jù)測(cè)試表明，系統(tǒng)安全可靠，可操作性強(qiáng)，能夠很好地實(shí)現(xiàn)風(fēng)電功率預(yù)測(cè)。
[Abstract]:With the large-scale wind power, wind power fluctuation and intermittence has brought severe challenges to the safe and stable operation of power system. Wind power prediction is one of the key technologies to solve large scale wind power integration, can provide technical support for the dispatch of power systems. The wind power prediction method research some achievements but not deep enough, the prediction system has just started, the lack of standardized and practical experience. It has important significance for wind power prediction method research.
In this paper, a wind farm is taken as the research object, and the wind speed distribution and wind power time characteristics of wind farms are systematically studied, in order to explore a more accurate prediction method of wind power. Meanwhile, a wind power prediction system is developed based on demand analysis.
First of all, with a wind farm as the object, the wind speed? Power characteristics were studied. The results show that the wind speed probability distribution of Weibull distribution characteristics; wind power randomness? Volatility and chaos, with time scale to reduce the volatility of wind power weakened.
Then, put forward a kind of empirical mode decomposition to (Empirical Mode Decomposition, EMD) wind power forecasting methods and phase space reconstruction is the core of the decomposed intrinsic mode functions (IntrinsicModel, Function, IMF) phase space reconstruction and residual components, the reconstructed sequence input support vector machine (Support Vector Machine SVM), the model of wind power forecasting. The results showed that after EMD decomposition reduces the modeling complexity, phase space reconstruction can reduce the influence of large deviation component on the prediction results, improve the prediction accuracy.
Secondly, based on meta learning wind power nonlinear combination forecasting model. The grey model? Time series model? Linear regression model and neural network model to predict the characteristics of results and the prediction of the sequence as the input element predictor, to discover and correct deviation system based pre sensor. In the predictor, determine the the base predictor weighted by the gating network function, ensure the time-varying and non negative weights. This algorithm is applied to predict wind power. The prediction results show that the algorithm prediction accuracy is higher than the combination of single prediction algorithm and the commonly used prediction algorithm.
Finally, according to the demand analysis, a wind power prediction system is developed, and the short-term prediction of wind power is realized. The test data of a wind farm show that the system is safe, reliable and operable, and it can achieve the prediction of wind power very well.

【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TM614

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王金山;楊國(guó)超;;一種基于時(shí)序可變加權(quán)系數(shù)的組合預(yù)測(cè)模型[J];重慶理工大學(xué)學(xué)報(bào)(自然科學(xué));2012年02期

2 冬雷;王麗婕;高爽;廖曉鐘;;基于混沌時(shí)間序列的大型風(fēng)電場(chǎng)發(fā)電功率預(yù)測(cè)建模與研究[J];電工技術(shù)學(xué)報(bào);2008年12期

3 張國(guó)強(qiáng);張伯明;;基于組合預(yù)測(cè)的風(fēng)電場(chǎng)風(fēng)速及風(fēng)電機(jī)功率預(yù)測(cè)[J];電力系統(tǒng)自動(dòng)化;2009年18期

4 張宜陽(yáng);盧繼平;孟洋洋;嚴(yán)歡;李輝;;基于經(jīng)驗(yàn)?zāi)Ｊ椒纸夂突煦缦嗫臻g重構(gòu)的風(fēng)電功率短期預(yù)測(cè)[J];電力系統(tǒng)自動(dòng)化;2012年05期

5 谷興凱;范高鋒;王曉蓉;趙海翔;戴慧珠;;風(fēng)電功率預(yù)測(cè)技術(shù)綜述[J];電網(wǎng)技術(shù);2007年S2期

6 潘迪夫;劉輝;李燕飛;;基于時(shí)間序列分析和卡爾曼濾波算法的風(fēng)電場(chǎng)風(fēng)速預(yù)測(cè)優(yōu)化模型[J];電網(wǎng)技術(shù);2008年07期

7 崔楊;穆鋼;劉玉;嚴(yán)干貴;;風(fēng)電功率波動(dòng)的時(shí)空分布特性[J];電網(wǎng)技術(shù);2011年02期

8 楊茂;賈云彭;錢(qián)為;陳琳;;基于動(dòng)態(tài)權(quán)重的風(fēng)電功率組合預(yù)測(cè)方法研究[J];東北電力大學(xué)學(xué)報(bào);2013年Z1期

9 華琦;王雷;陸金桂;杜杰;;基于混沌理論與神經(jīng)網(wǎng)絡(luò)的短期風(fēng)速滾動(dòng)預(yù)測(cè)[J];電測(cè)與儀表;2013年07期

10 植雅芳;;基于SSH框架的在線考試系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];福建電腦;2013年11期

相關(guān)博士學(xué)位論文 前3條

1 楊志凌;風(fēng)電場(chǎng)功率短期預(yù)測(cè)方法優(yōu)化的研究[D];華北電力大學(xué)（北京）;2011年

2 仝紀(jì)龍;河西地區(qū)風(fēng)速變化特征及風(fēng)能預(yù)測(cè)方法研究[D];蘭州大學(xué);2012年

3 靳雙龍;中尺度WRF模式在風(fēng)電功率預(yù)測(cè)中的應(yīng)用研究[D];蘭州大學(xué);2013年

本文編號(hào)：1553053