论文(设计)基于时间序列法的风电场风速预测研究.doc

上传人:文库蛋蛋多 文档编号:3992949 上传时间:2023-03-30 格式:DOC 页数:7 大小:279KB
返回 下载 相关 举报
论文(设计)基于时间序列法的风电场风速预测研究.doc_第1页
第1页 / 共7页
论文(设计)基于时间序列法的风电场风速预测研究.doc_第2页
第2页 / 共7页
论文(设计)基于时间序列法的风电场风速预测研究.doc_第3页
第3页 / 共7页
论文(设计)基于时间序列法的风电场风速预测研究.doc_第4页
第4页 / 共7页
论文(设计)基于时间序列法的风电场风速预测研究.doc_第5页
第5页 / 共7页
点击查看更多>>
资源描述

《论文(设计)基于时间序列法的风电场风速预测研究.doc》由会员分享,可在线阅读,更多相关《论文(设计)基于时间序列法的风电场风速预测研究.doc(7页珍藏版)》请在三一办公上搜索。

1、基于时间序列法的风电场风速预测研究邵 璠1,孙育河1,梁岚珍2(1.新疆大学电气工程学院1,乌鲁木齐 830008;2.北京联合大学自动化学院2,北京100101)摘 要:采用Box.Jenkins时间序列分析方法, 通过Matlab软件,利用达坂城风电场30米处,每10分钟采集一次得到的风速数据,建立ARMA模型,实现提前一小时的风速预测,为更长时间(半天、一天或两天)的风速预测提供理论基础。关键词:时间序列;风速预测;ARMA模型中图分类号:TK8 文献标识码:A0 引言目前,世界上可再生能源增长最快的就是风电,据政府计划,到2020年我国风电的装机容量将达到3000万kw1。风电能占整个

2、电网比例的大小取决于很多因素,其中一个最重要的是风速的可预测性。风速预测精度的提高可以降低所需的储备电能,并增加电网的可靠性,具有很大的经济意义。这对于电网调度和资源配置非常有必要。而风速预测主要集中在0-3小时时间段。这个时间范围是电网调度,资源配置所需时间2。风速预测按技术分为三类:数字天气预报,统计方法和神经网络预报方法。其中统计技术和神经网络预报方法以观测数据为基础,在超短期预测时段精度更高。时间序列模型最为简单,所以也是花费最小的风速预测模型。它仅仅需要最近几个小时风速数据就可对未来风速进行预测。它的主要手段是对各类数据用相应的数学模式去近似描述,进一步达到预测的目的。对于采用何种建

3、模方案,也就是如何对这些观测数据建立数学模型,人们进行了大量的研究,本文主要针对时间序列的超短期风速预测进行研究。1 时间序列法风速是一种随机变量,Box.Jenkins方法是随机时间序列分析的主要方法之一,已被用于风速预测。它利用历史数据来建模,经过模型识别、参数估计、模型检验来确定一个能够描述所研究时间序列的数学模型,再由该模型推导出预测模型。根据Box-Jenkins方法,可将随机时间序列的预测模型分类为:自回归模型(AR)、滑动平均模型(MA)、自回归滑动平均模型(ARMA)。AR 模型,当前时刻的观测值由过去几个历史时刻的观测值和一个当前时刻的随机干扰来表示;MA 模型,当前时刻的观

4、测值由称作随机干扰的白噪声序列的线性组合来表示;将AR 模型与MA 模型结合起来,即ARMA 模型3。2 建立预测模型2.1 数据预处理本文中选用新疆达坂城风力发电站2007年1月2日到1月31日的风速数据,数据为10分钟采集一次。一月份平均风速8.7212m/s,风能资源良好。由时间序列模型的特性可知,AR, MA, ARMA模型所适合描述的对象应是均值为零的平稳随机序列,然而实际的建模对象往往既包括平稳的随机部分,又含有确定的非随机分量。因此,在进行时间序列建模时,首先需要对观测数据序列迸行平稳化处理,使非平稳的数据序列转化为均值为零的平稳随机序列。差分公式为:t = dZt差分后,自相关

5、函数很快衰减,相应的d就设定为达到平稳所需的差分阶数。在实际中,d通常为0,1或2,并且通常考察原序列、一阶或二阶差分序列自相关函数估计值的前15-25个就够了3。测量数据200个,下图是原始数据、数据经过1阶差分和2阶差分后的自相关函数图(前20个数据)。2阶差分的自相关函数更快速的收敛,所以差分阶数为2。图1 数据预处理Fig.1 data preprocessing2.2 模型参数识别2.2.1 模型结构识别简要地说,p阶自回归过程的自相关是拖尾的,而它的偏相关函数在滞后p步之后是截尾的。q阶滑动平均过程的自相关函数在滞后q步之后是截尾的,而它的偏相关函数是拖尾的。而混合过程的自相关和偏

6、相关函数都是拖尾的4。观察数据的自相关和偏相关图,本文选用ARMA模型。2.2.2 参数初估计图2 差分数据的相关函数Fig.2 The correlation function of differential data根据acf和pacf图,Z的自相关在4步滞后之后就很小,其偏向关函数在3步后,值就很小,这表示该时间序列可以用ARMA(3,4)模型来描述。2Z的自相关在4步滞后之后就很小,这表示该时间序列可以用ARMA(0,3)模型来描述。模型参数也可以通过自相关和偏向关函数来确定,偏相关函数= 0的时候,AR序列的阶数na = k1,自相关函数k = 0,MA序列的阶数nc = k1。分析

7、下面表格内数据后会发现,同1相比,2 3 4更接近于零,而3 4比2又小很多,所以AR 阶次为2或3。比较偏相关系数,很明显,更接近于零,而,同相比则更小,所以MA阶次为2或3,分析数据可以看出,由于数据经过一阶差分,10段数据的Y2都比较小,这说明数据震荡性不大。从平均风速可以知道,4 - 7段以及第10段的平均风速都较低,也就说明2007年1月份中,11日到22日,29日到31日的风能质量比较低。其他时间平均风速在10m/s以上,风速质量良好。2.3 模型诊断、检验2.3.1 确定风速训练数据风速数据过少可能导致预测精度较低,而且模型参数需要利用充足的数据通过计算得到,实际操作中数据值低于

8、100的时候,较高阶的模型的参数无法获取,在100300段获取的模型预测效果比较好,我们在这之间选取最适合的数据量。选取100, 150, 200, 250, 300作为数据量。当训练数据为100的时候,RMSE和MAE相比其他的数目的更小,因此训练数据量为100。2.3.2 参数识别1模型匹配值fit定阶,fit=100(1-风速测量值风速预测值/风速测量值平均风速)5。方差的大小表示的是实际风速的波动性。第一段的各个模型fit相差不大,而2, 3, 7, 9, 10段,ARMA(3,4)的fit值最大,选择它进行预测比较合适。而1, 6段选择(2,3)模型比较合适。4, 5, 8段选用(3

9、,2)模型比较合适。通过比较可以发现,ARMA(3,4)适合用在方差较小的区域,方差一般在14左右的区域,仔细观察,同样方差较小的1, 4段中虽然是其他模型的fit值最小,仔细观察后发现,其实各个模型的fit值差距很小,差值在1以内。因此在方差较小的时候,选择ARMA(3,4)模型进行预测。在方差较大的时候,如5, 8段选择ARMA(3,2)。表1 自相关和偏相关函数表Table 1 autocorrelation and partial correlation function Table表2 各风速段fit值比较Table 2 compared fit of the wind2AIC定阶,

10、AIC函数为 (1) 选取不同的p, q值及模型参数,运用MATLAB6.5工具箱中的aic ( ) 函数对序列进行拟合,使AIC值达到极小的模型被认为是最佳模型。实际上,AIC最小的时候,就是拟合函数的残差方差最小的时候,因此得予 到的p, q值为最佳选择6。比较后发现,通过AIC法则确定的模型与fit值比较后得到的结果一致,各模型的aic值不详细列出。3模型检验平稳可逆性检验:当A (q) = 0和C (q) = 0的时候,求得根q都在单位圆外,满足稳定性和可逆性。由于数据众多,这里不以列出。残差序列检验:四个风速段中,残差序列的自相关函数绝对值中最大值分别为0.1717,0.1829,0

11、.1853,0.1287,而=0.197,(n=N-d=99,n为考虑差分后用于拟合的有效样本容量,N为原始数据数量,d为差分次数),它们均小于0.197,综合上面两项结果,模型残差可视作白噪声4,模型拟合效果良好。所以选择ARMA(3,4)来进行预测,公式如下,各风速段选用的模型参数见图3。表3 各风速段选用的模型参数3 预测及结果分析选择第7, 2, 9风速段的数据分别代表低、中和高风速段,分别进行预测分析,见图3。低风速段 Low wind中风速段Middle wind 高风速High wind图3 各风速段的预测结果与误差分析Figure 3 the speed of the pred

12、icted results and error analysis通过以上数据可以看出,风速对于相对误差的影响最大,远大于预测长度对它的影响。7和2段属于低风速段,但是偏差却高于其他风速段。9段是风速较高,偏差却是所有风速段中最小的。而且,风速震荡大,偏差震荡也大。7段与2,9段比较可以观察到这一点;风速出现突然跳跃的时候,相对误差也比较大;列表中可以看到,2段中的风速相对误差是最大的,在风速值出现了较大跳跃点的位置,偏差值最大;预测时间越长,偏差越大,具体数据见表4。表4 不同风速段的预测误差Table 4 different speed of the prediction error风速段M

13、MW S (m/s)R E(%)MAE (m/s)RMSE (m/s)71.9830.11020.50390.521927.2940.13550.76821.1444920.341-0.09410.80611.29994 总结四个风速段的相对误差在10%左右,MAE和RE在1m/s以内,数据见表4。这也证明本文的预测方法可以较为准确的对风速进行提前一小时预测。利用ARMA(3,4)模型进行预测,最终预测误差在10%左右,通过分析预测结果,风速序列的震荡性对于预测结果的影响远大于预测长度的影响,因此预测长度还可以有所增加。这也就为更长时间(半天、一天或两天)的风速预测提供理论基础。参考文献1 “

14、Wind Force 12”, Report by the European Wind Energy Association (EWEA), October 2002,2 杨秀媛,肖洋,陈树勇.风电场风速和发电功率预测研究J.中国电机工程学报,2005,25(11):1-5.3 张善文.Matlab在时间序列分析中的应用M.西安:西安电子科技大学出版社,2007.4.4 S. Pashardes, C. Christofides, Statistical Analysis of Wind Speed and Direction in CyprusJ, Solar Energy, 1995, 5

15、5(5): 405 - 414.5 Milligan, M., M Schwartz, Y. Wan.Statistical Wind Power Forecasting Models: Results for U.S. Wind FarmsJ. Windpower, 2003, Austin, TX, AWEA.6 时间序列分析M(美)恩德斯等著,杜江,谢志超译.北京:高等教育出版社,2006.6STUDY ON THE TIME-SERIES WIND SPEED FORECASTING OF THE WIND FARM BASED ON TIME SERIES Shao fan, Sun

16、 Yu-he, Liang Lan-zhen(1.College of Electrical Engineering,Xinjiang University,Urumqi 830008 China;2.College of Automation,Beijing Union University,Beijing 100101 China)Abstract:Using the speed data obtained from Dabancheng wind farm every 10 minute where is 30 meters high, through Matlab software,

17、wind speed forcasting of the wind farm one hour in advance is realized by the time-series analysis method of Box. Jenkins.Key word:time series;wind speed forecasting;ARMA model项目基金:新疆教育基金高新技术重点项目(项目批号:XJEDU2005I02)作者简介:邵璠(1982),女,汉族,辽宁锦州人,硕士研究生,主要从事计算机控制与自动化网络方面的研究。spoon19820707孙育河(1983),男,汉族,陕西咸阳人,

18、硕士研究生,主要从事计算机控制与自动化网络方面的研究。 sunyuhe8382 梁岚珍(1957),女,汉族,山西岚县人,教授,硕士生导师,主要从事计算机控制与自动化网络方面的科研与教学工作。lianglanzhen通讯作者:新疆乌鲁木齐市西北路134号新疆大学(北校区)电气工程学院05级研究生(邵璠)收 邮编:830008 电话:1999863406 Email: spoon19820707Editors note: Judson Jones is a meteorologist, journalist and photographer. He has freelanced with CNN

19、 for four years, covering severe weather from tornadoes to typhoons. Follow him on Twitter: jnjonesjr (CNN) - I will always wonder what it was like to huddle around a shortwave radio and through the crackling static from space hear the faint beeps of the worlds first satellite - Sputnik. I also miss

20、ed watching Neil Armstrong step foot on the moon and the first space shuttle take off for the stars. Those events were way before my time.As a kid, I was fascinated with what goes on in the sky, and when NASA pulled the plug on the shuttle program I was heartbroken. Yet the privatized space race has

21、 renewed my childhood dreams to reach for the stars.As a meteorologist, Ive still seen many important weather and space events, but right now, if you were sitting next to me, youd hear my foot tapping rapidly under my desk. Im anxious for the next one: a space capsule hanging from a crane in the New

22、 Mexico desert.Its like the set for a George Lucas movie floating to the edge of space.You and I will have the chance to watch a man take a leap into an unimaginable free fall from the edge of space - live.The (lack of) air up there Watch man jump from 96,000 feet Tuesday, I sat at work glued to the

23、 live stream of the Red Bull Stratos Mission. I watched the balloons positioned at different altitudes in the sky to test the winds, knowing that if they would just line up in a vertical straight line we would be go for launch.I feel this mission was created for me because I am also a journalist and

24、 a photographer, but above all I live for taking a leap of faith - the feeling of pushing the envelope into uncharted territory.The guy who is going to do this, Felix Baumgartner, must have that same feeling, at a level I will never reach. However, it did not stop me from feeling his pain when a gus

25、t of swirling wind kicked up and twisted the partially filled balloon that would take him to the upper end of our atmosphere. As soon as the 40-acre balloon, with skin no thicker than a dry cleaning bag, scraped the ground I knew it was over.How claustrophobia almost grounded supersonic skydiverWith

26、 each twist, you could see the wrinkles of disappointment on the face of the current record holder and capcom (capsule communications), Col. Joe Kittinger. He hung his head low in mission control as he told Baumgartner the disappointing news: Mission aborted.The supersonic descent could happen as ea

27、rly as Sunday.The weather plays an important role in this mission. Starting at the ground, conditions have to be very calm - winds less than 2 mph, with no precipitation or humidity and limited cloud cover. The balloon, with capsule attached, will move through the lower level of the atmosphere (the

28、troposphere) where our day-to-day weather lives. It will climb higher than the tip of Mount Everest (5.5 miles/8.85 kilometers), drifting even higher than the cruising altitude of commercial airliners (5.6 miles/9.17 kilometers) and into the stratosphere. As he crosses the boundary layer (called the

29、 tropopause), he can expect a lot of turbulence.The balloon will slowly drift to the edge of space at 120,000 feet (22.7 miles/36.53 kilometers). Here, Fearless Felix will unclip. He will roll back the door.Then, I would assume, he will slowly step out onto something resembling an Olympic diving pla

30、tform.Below, the Earth becomes the concrete bottom of a swimming pool that he wants to land on, but not too hard. Still, hell be traveling fast, so despite the distance, it will not be like diving into the deep end of a pool. It will be like he is diving into the shallow end.Skydiver preps for the b

31、ig jumpWhen he jumps, he is expected to reach the speed of sound - 690 mph (1,110 kph) - in less than 40 seconds. Like hitting the top of the water, he will begin to slow as he approaches the more dense air closer to Earth. But this will not be enough to stop him completely.If he goes too fast or sp

32、ins out of control, he has a stabilization parachute that can be deployed to slow him down. His team hopes its not needed. Instead, he plans to deploy his 270-square-foot (25-square-meter) main chute at an altitude of around 5,000 feet (1,524 meters).In order to deploy this chute successfully, he wi

33、ll have to slow to 172 mph (277 kph). He will have a reserve parachute that will open automatically if he loses consciousness at mach speeds.Even if everything goes as planned, it wont. Baumgartner still will free fall at a speed that would cause you and me to pass out, and no parachute is guarantee

34、d to work higher than 25,000 feet (7,620 meters).It might not be the moon, but Kittinger free fell from 102,800 feet in 1960 - at the dawn of an infamous space race that captured the hearts of many. Baumgartner will attempt to break that record, a feat that boggles the mind. This is one of those monumental moments I will always remember, because there is no way Id miss this.

展开阅读全文
相关资源
猜你喜欢
相关搜索

当前位置:首页 > 办公文档 > 其他范文


备案号:宁ICP备20000045号-2

经营许可证:宁B2-20210002

宁公网安备 64010402000987号