A Divided-time Forecasting Model of Wind Speed in Wind Farm Based on Improved Spatial Correlation an.docVIP

下载本文档

2
0
约1.02万字
约 13页
2017-08-31 发布于湖北
举报
版权申诉

A Divided-time Forecasting Model of Wind Speed in Wind Farm Based on Improved Spatial Correlation an.doc

1、本文档共13页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

A Divided-time Forecasting Model of Wind Speed in Wind Farm Based on Improved Spatial Correlation an.doc

2013—论文：基于改进空间相关法和径向基神经网络的风电场短期风速分时预测模型 A Divided-time Forecasting Model of Wind Speed in Wind Farm Based on Improved Spatial Correlation and RBF Neural Network 李文良1，卫志农2，孙国强2 LI Wenliang,WEI Zhinong,SUN Guoqiang,WAN Zheng,MIAO Wei （1. 福建省电力有限公司检修分公司2.河海大学电气工程学院，南京210098） (1.Hohai University Nanjing 210098 China; 2.Wuhu Power Supply Company Wuhu 241000) 摘要：空间相关法是从风的物理特性出发，利用空间相关点风速数据之间的相似性和延时性来进行风速预测的方法。针对空间相关法在实际应用中存在数据收集困难的问题，提出用空间平移法对空间相关法进行改进，从而有效地降低数据收集的难度。为了确定空间相关点风速与所需预测的风电场风速数据之间的非线性关系，采用径向基(RBF)神经网络，建立了基于空间相关法的分时预测模型。该方法通对风电场与空间相关点风速时间序列之间的关联度分析，将未来预测时段分成若干个时段，在每个时段内分别选择关联度高的相关点的风速数据，作为RBF神经网络的输入数据，进行训练和预测。通过算例表明，该方法不仅提高了风电场风速预测的预测精度，同时减少了RBF神经网络的训练时间。 ABSTRACT: The spatial correlation models consider the physical characteristic of wind, and it forecast the wind speed of wind farm based on the similarity and delaying between wind speed of wind farm and that of correlative sites. For reducing the difficulty of data collection in correlative sites, a method of spatial translation is used to improve the method of spatial correlation. In this paper, Radial Basis Function (RBF) neural network is used to find the nonlinear relation of wind speed between the wind speed of wind farm and that of correlative sites, and a divided-time forecasting model based on the spatial correlation is also suggested. In this model, the wind speed data correlation analysis between local and reference sites is analyzed, and then the forecasting time is divided into some interval-times. In each interval-time, the wind speed data of reference site which has the better correlation to wind farm, is chosen as the input data of RBF neural network to train and forecast the wind speed. The predicted result shows that the proposed approach improve the accuracy of predicting the wind speed, and it can also shorten the training time of RBF neural network. 关键词：短期风速预测;空间相关法;分时预测;空间平移法;RBF神经网络 KEY WORD: wind speed forecasting; spatial correlation; divided-time forecasting model; spatial t