张介,马赟,张旭鹏,刘高明
ZHANG Jie,MA Yun,ZHANG Xupeng,LIU Gaoming

• 1:国网浙江省电力有限公司湖州供电公司
• 2:国网河北省电力有限公司保定供电分公司

摘要(Abstract)：

随着我国风电装机容量的逐步增加,风电在电源结构中的比例也进一步增大,而风电出力本身的随机性、波动性使得风电出力预测工作难度增加。鉴于不同特性的气象数据对应的出力差异性很大,因此采用模糊C均值聚类分析方法将风电场运行历史气象信息进行聚类并训练相应的BP神经网络,再将数值天气预报提供的待预测日的气象信息进行聚类,根据数据的聚类中心将待预测日气象信息与历史数据进行归类,最后将同一类风速、风向数据结合相应的BP神经网络进行预测。算例分析证明了此方法的有效性。
With the increase of installed capacity of wind power in China, the proportion of wind power in the energy mix further increases. Due to its randomness and fluctuation, it is difficult to forecast the wind power output. In the wind farm, different meteorological data result in differences in wind power. So historical data of wind farms are gathered by using cluster analysis of fuzzy C-means; then the BP neural network is trained by the clustered data. The next stop is clustering the meteorological data provided by the NWP of next day.Every clustered data has a cluster center. The clustered data of the two days are classified according to the cluster centers. Finally, the same type of clustered data of wind speed and direction are used to simulate by using the BP neural network. The calculation example verifies the effectiveness of the method.

关键词(KeyWords)： 风电场;出力预测;聚类分析;BP神经网络
wind farm;output forecast;cluster analysis;BP neural network

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 张介,马赟,张旭鹏,刘高明
ZHANG Jie,MA Yun,ZHANG Xupeng,LIU Gaoming

DOI: 10.19585/j.zjdl.201801009

参考文献(References)：

• [1]周双喜,鲁宗相.风力发电与电力系统[M].北京:中国电力出版社,2011.
• [2]孙涛,王伟胜,戴慧珠,等.风力发电引起的电压波动和闪变[J].电网技术,2003,27(12):63-70.
• [3]迟永宁,刘燕华,王伟胜,等.风电接入对电力系统的影响[J].电网技术,2007,3(13):77-81.
• [4]王健,严干贵,宋薇,等.风电功率预测技术综述[J].东北电力大学学报,2011,31(3):20-24.
• [5]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.
• [6]于大洋,韩学山,梁军,等.基于NASA地球观测数据库的区域风电功率波动特性分析[J].电力系统自动化,2011,35(5):77-82.
• [7]冯双磊,王伟胜,刘纯.风电场功率预测物理方法研究[J].中国电机工程学报,2010,30(2):1-6.
• [8]谷兴凯,范高锋,王晓蓉,等.风电功率预测技术综述[J].电网技术,2007,31(2):335-338.
• [9]范高锋,王伟胜,刘纯.基于人工神经网络的风电功率短期预测系统[J].电网技术,2008,32(22):72-76.
• [10]ALEXIADIS M,DOKOPOULOS P,SAHSAMANOGLOUH.Short term forecasting of wind speed and related electrical power[J].Solar Energy,1998,63(1):61-68.
• [11]A SFETSOS.A comparison of various forecasting techniques applied to mean hourly wind speed time series[J].Renewable Energy,2000(21):23-35.
• [12]MOHAMEDA MOHANDES,SHAFIQUR REHMAN,TA-LALO HALAWANI.A neural networks approach for wind speed prediction[J].Renewable Energy,1998,13(3):345-354.
• [13]刘艳华,刘冲,李伟花,等.基于出力模式匹配的风电集群电多时间尺度功率预测[J].中国电机工程学报,2014,34(25):4350-4358.
• [14]陈颖,孙荣富,吴志坚,等.基于统计升尺度方法的区域风电场群功率预测[J].电力系统自动化,2013,37(7):1-5.
• [15]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术[M].北京:科学出版社,2007.
• [16]陈祥光,裴旭东.人工神经网络技术及应用[M].北京:中国电力出版社,2003.
• [17]GIEBEL G,BADGER J,MART魱PEREZ I.Short-term forecasting using advanced physical mod-elingthe results of the anems project results from mesoscale,microscale and CFD modelling[C]//European Wind Energy Conference&Exhibition,Athens,Greece,2006.
• [18]FOCKEN U M,LANGE H P W.Previento-a wind power prediction system with an inno-vative upscalingalgorithm[C]//European Wind Energy Conference,2001.
• [19]BERNHARD L,KURT R,BERNHARD E,et al.Wind power prediction in Germany-recent adva-nces and future challenges[C]//European Wind Energy Conference,Athens,2006.
• [20]LI S.Wind Power Prediction Using Recurrent Multilayer Perceptron Neural Networks[C]//IEEE Power Engineering Society General Meeting,2003.
• [21]BERNHARD L,KURT R.Wind power prediction in Germany-recent advances and future c-hallenges[C]//European Wind Energy Conference,Athens,2006.
• [22]范高锋,王伟胜,刘纯,等.基于人工神经网络的风电功率预测[J].中国电机工程学报,2008,28(34):118-123.
• [23]杜颖,卢继平,李青,等.基于最小二乘支持向量机的风电场短期风速预测[J].电网技术,2008,32(15):62-66.
• [24]潘迪夫,刘辉,李燕飞.基于时间序列分析和卡尔曼滤波算法的风电场风速预测优化模型[J].电网技术,2008,32(7):82-86.
• [25]董朕,殷豪,孟安波.基于混合算法优化神经网络的风电预测模型[J].广东电力,2017,30(2):29-33.
• [26]LANDBERG L,GIEBEL G,NIELSEN H AA,et al.Shortterm Prediction-An overview[J].Wind Energy,2003,6(3):273-280.