本文選題：風(fēng)電功率 + 超短期預(yù)測　； 參考：《東北電力大學(xué)》2017年碩士論文

【摘要】：在我國,風(fēng)電是目前最有潛力的,可以大力發(fā)展的非水電可再生能源。但同時風(fēng)能的諸多自身特性,包括隨機性、不確定性等,使大規(guī)模風(fēng)電并網(wǎng)存在一些困難。為了實現(xiàn)大規(guī)模風(fēng)能的開發(fā)利用,以超短期風(fēng)電功率預(yù)測為背景,吉林省多個風(fēng)電場的實測數(shù)據(jù)為基礎(chǔ),從風(fēng)電功率的數(shù)據(jù)補齊、多步滾動的預(yù)測方法、風(fēng)電功率預(yù)測的不確定性分析以及預(yù)測誤差的非參數(shù)擬合四個方面進行了全面的分析與研究。對于風(fēng)力發(fā)電的特性分析、功率預(yù)測、儲能配置等研究都需要在歷史數(shù)據(jù)的基礎(chǔ)上進行展開,但實際中往往會由于各種原因?qū)е聰?shù)據(jù)不完整,缺失的數(shù)據(jù)可能會使系統(tǒng)變得混亂、難控制,或者存在越來越多的不確定性變化,這些情況都會對后續(xù)的分析估計造成很大的障礙�；谧畲笙嚓P(guān)最小冗余原則對風(fēng)電場風(fēng)電功率數(shù)據(jù)進行補齊,首先分析得出與功率有關(guān)的變量,然后根據(jù)互信息理論,對變量通過最大相關(guān)最小冗余的原則進行特征選取,挖掘特征與功率之間的聯(lián)系,最后根據(jù)這種聯(lián)系對功率數(shù)據(jù)進行補齊。結(jié)果表明特征選取是對高維數(shù)據(jù)進行降維的有效辦法,從原始特征集中選出特征子集,保留原始特征集的有效信息,從而補齊缺失的數(shù)據(jù)。風(fēng)電功率預(yù)測的準(zhǔn)確率越高,風(fēng)能的利用率越高,因此,需要確定合理有效的預(yù)測方法,建立多步滾動的風(fēng)電功率預(yù)測模型。相關(guān)向量機(RVM)是一種稀疏概率模型的學(xué)習(xí)機,具有很好的泛化學(xué)習(xí)能力,能有效地預(yù)測風(fēng)電功率并且運行時間極快。同時引入集合經(jīng)驗?zāi)B(tài)分解(EEMD),將功率數(shù)據(jù)的初始序列分解成若干組平穩(wěn)的序列,該方法可以顯著提高預(yù)測精度,縮短運行時間。由于任何預(yù)測都具有不確定性,因此帶有置信區(qū)間的單點預(yù)測范圍可以降低電網(wǎng)和風(fēng)電場運行的風(fēng)險,整個系統(tǒng)的運行也就更安全穩(wěn)定。對風(fēng)電功率預(yù)測的不確定性進行分析,可以把預(yù)測功率的單一值轉(zhuǎn)化成功率的估計區(qū)間。結(jié)果表明相關(guān)向量機的預(yù)測模型可以提供給定置信水平下的預(yù)測波動范圍。對預(yù)測誤差進行擬合分布評價,通過對預(yù)測誤差的分布特征可以分析得出非參數(shù)估計與預(yù)測方法、預(yù)測時間間隔、預(yù)測誤差概率分布形態(tài)以及風(fēng)電場裝機容量的關(guān)系,從而使系統(tǒng)穩(wěn)定持續(xù)地運行。結(jié)果表明非參數(shù)估計分布模型對不同規(guī)模的風(fēng)電場和不同條件的分布均能較好地擬合,其中單峰的擬合效果更好。
[Abstract]:Wind power is the most potential non-hydropower renewable energy in China. But at the same time, wind energy has many characteristics, such as randomness and uncertainty, which makes large-scale wind power grid difficult. In order to realize the development and utilization of large-scale wind energy, based on the forecast of ultra-short-term wind power and the measured data of several wind farms in Jilin Province, the prediction method of wind power compensation and multi-step rolling is introduced. The uncertainty analysis of wind power prediction and the nonparametric fitting of prediction error are analyzed and studied comprehensively. For wind power generation characteristics analysis, power prediction, energy storage configuration and other studies need to be carried out on the basis of historical data, but in practice, due to various reasons, the data are often incomplete. The missing data may make the system chaotic, difficult to control, or there are more and more uncertain changes, which will cause great obstacles to the subsequent analysis and estimation. Based on the principle of maximum correlation and minimum redundancy, the wind power data of wind farm is compensated. Firstly, the variables related to power are analyzed, and then, according to the mutual information theory, the variables are selected by the principle of maximum correlation and minimum redundancy. The relation between feature and power is mined, and the power data is corrected according to this relation. The results show that feature selection is an effective method to reduce the dimension of high-dimensional data. The feature subset is selected from the original feature set, and the effective information of the original feature set is retained. The higher the accuracy of wind power prediction, the higher the utilization rate of wind energy. Therefore, it is necessary to determine a reasonable and effective forecasting method and to establish a multi-step rolling wind power prediction model. Correlation vector machine (RVM) is a kind of learning machine with sparse probability model. It has good generalization ability and can effectively predict wind power and run very fast. At the same time, the set empirical mode decomposition (EMD) is introduced to decompose the initial sequence of power data into a number of stationary sequences. This method can significantly improve the prediction accuracy and shorten the running time. Because of the uncertainty of any prediction, the single point prediction range with confidence interval can reduce the risk of power grid and wind farm operation, and the operation of the whole system is safer and more stable. By analyzing the uncertainty of wind power prediction, the single value of predicted power can be transformed into the estimated interval of success rate. The results show that the prediction model of correlation vector machine can provide the range of predicted fluctuations at a given confidence level. The relationship between nonparametric estimation and prediction method, prediction time interval, probability distribution pattern of prediction error and installed capacity of wind farm can be obtained by analyzing the distribution characteristics of prediction error. Thus, the system runs steadily and continuously. The results show that the non-parametric distribution model can fit the distribution of wind farms of different scale and different conditions, and the fitting effect of single peak is better.
【學(xué)位授予單位】：東北電力大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TM614

【參考文獻】

相關(guān)期刊論文 前10條

1 葉超;郝付軍;;基于支持向量機和BP神經(jīng)網(wǎng)絡(luò)的滑坡變形復(fù)合式預(yù)測[J];水土保持通報;2016年03期

2 劉波;賀志佳;金昊;;風(fēng)力發(fā)電現(xiàn)狀與發(fā)展趨勢[J];東北電力大學(xué)學(xué)報;2016年02期

3 楊茂;季本明;;基于局域一階加權(quán)法的風(fēng)電功率超短期預(yù)測研究[J];東北電力大學(xué)學(xué)報;2015年05期

4 楊德友;蔡國偉;;基于因散經(jīng)驗?zāi)Ｊ椒纸馀c最小二乘支持向量機的風(fēng)電場短期風(fēng)速預(yù)測[J];東北電力大學(xué)學(xué)報;2015年03期

5 楊茂;呂天峰;季本明;;混沌理論在電力系統(tǒng)負(fù)荷預(yù)測中應(yīng)用綜述[J];東北電力大學(xué)學(xué)報;2015年03期

6 張元;郝麗麗;戴嘉祺;;風(fēng)電場等值建模研究綜述[J];電力系統(tǒng)保護與控制;2015年06期

7 劉燕華;李偉花;劉沖;張東英;;短期風(fēng)電功率預(yù)測誤差的混合偏態(tài)分布模型[J];中國電機工程學(xué)報;2015年10期

8 劉芳;潘毅;劉輝;丁強;李強;王芝茗;;風(fēng)電功率預(yù)測誤差分段指數(shù)分布模型[J];電力系統(tǒng)自動化;2013年18期

9 劉立陽;吳軍基;孟紹良;;短期風(fēng)電功率預(yù)測誤差分布研究[J];電力系統(tǒng)保護與控制;2013年12期

10 高虎;王紅芳;;2012年我國風(fēng)電市場發(fā)展綜述[J];中國能源;2013年04期

相關(guān)碩士學(xué)位論文 前4條

1 陳辰;基于卡爾曼濾波算法的短期風(fēng)電功率預(yù)測[D];新疆大學(xué);2015年

2 曹靜;基于最大相關(guān)最小冗余的特征選擇算法研究[D];燕山大學(xué);2010年

3 肖軒;灰色神經(jīng)網(wǎng)絡(luò)與支持向量機預(yù)測模型研究[D];武漢理工大學(xué);2009年

4 張成萍;殘缺數(shù)據(jù)的填補[D];中南大學(xué);2006年

，

本文編號：1952593