鲁宗相;李剑楠;乔颖;赵俊屹;杨超颖;

• 1:电力系统及发电设备控制和仿真国家重点实验室(清华大学)
• 2:国网山西省电力公司

摘要(Abstract)：

准确预估自然状态下的风资源是进行风电优化调度的基础。为了充分利用多数据源实现有用信息的筛选和提取来提高预估精度,同时有效控制数据规模和复杂性,在风资源超短期预估中引入数据预处理环节是必要的。因此提出了基于复相关系数的数据筛选方法及基于典型相关分析的序列降维方法,构建了多维到1维序列映射模型用于多数据源的质量提升和降维简化,作为前置数据处理环节纳入到基于遗传算法和反向传播(back propagation,BP)神经网络的风资源超短期预估方法中。最后通过实际算例证明了该数据预处理方法在提高预估精度方面具有显著的效果。

关键词(KeyWords)： 风资源;多数据源;降维技术;数据筛选;预估方法

Abstract:

Keywords:

基金项目(Foundation): 国家863高技术基金项目(2011AA05A103);; 国家自然科学基金项目(51190101)~~

作者(Author): 鲁宗相;李剑楠;乔颖;赵俊屹;杨超颖;

Email:

DOI: 10.13335/j.1000-3673.pst.2015.05.016

参考文献(References)：

• [1]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.Fan Gaofeng,Wang Weisheng,Liu Chun.Artificial neural network based wind power short term prediction system[J].Power System Technology,2008,32(22):72-76(in Chinese).
• [2]Palomares-Salas J C,De-La-Rosa J J G,Ramiro J G,et al.ARIMA vs.neural networks for wind speed forecasting[C]//2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.Hong Kong,China:IEEE,2009:129-133.
• [3]李文良,卫志农,孙国强,等.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[J].电力自动化设备,2009,29(6):89-92.Li Wenliang,Wei Zhinong,Sun Guoqiang,et al.Multi-interval wind speed forecast model based on improved spatial correlation and RBF neural network[J].Electric Power Automation Equipment,2009,29(6):89-92(in Chinese).
• [4]Schlueter R A,Park G L,Bouwmeester R,et al.Simulation and assessment of wind array power variations based on simultaneous wind speed measurements[J].IEEE Transactions on Power Apparatus and Systems,1984,PAS-103(5):1008-1016.
• [5]Alexiadis M C,Dokopoulos P S,Sahsamanoglou H S,et al.Shor-term forecasting of wind speed and related electrical power[J].Solar Energy,1998,63(1):61-68.
• [6]Schlueter R A,Sigari G,Costi A.Wind array power prediction for improved operating economics and reliability[J].IEEE Transactions on Power Apparatus and Systems,1985,PAS-104(7):137-142.
• [7]郭创新,王扬,沈勇,等.风电场短期风速的多变量局域预测法[J].中国电机工程学报,2012,32(1):24-31.Guo Chuangxin,Wang Yang,Shen Yong,et al.Multivariate local prediction method for short-term wind speed of wind farm[J].Proceedings of the CSEE,2012,32(1):24-31(in Chinese).
• [8]陈忠.基于BP神经网络与遗传算法风电场超短期风速预测优化研究[J].可再生能源,2012,30(2):32-36.Chen Zhong.Optimazation study on ultra-short term wind speed forecasting of wind farms based on BP neural network and genetic algorithm[J].Renewable Energy,2012.30(2):32-36(in Chinese).
• [9]王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报:工学版,2012,46(5):837-841.Wang Deming,Wang Li,Zhang Guangming.Short-term wind speed forecast model for wind farms based on genetic BP neural network[J].Journal of Zhejiang University:Engineering Science Edition,2012,46(5):837-841(in Chinese).
• [10]王小平,曹立明.遗传算法:理论、应用与软件实现[M].西安:西安交通大学出版社,2002:51-86.
• [11]周复恭,黄运成.应用线性回归分析[M].北京:中国人民大学出版社,1989:28-59.
• [12]吴洪宝,吴蕾.气候变率诊断和预测方法[M].北京:气象出版社,2005:1-35.
• [13]赖艺芬,梁飞豹.基于典型相关的线性回归模型[J].福州大学学报:自然科学版,2004,32(4):438-441.Lai Yifen,Liang Feibao.Linear regression model based on canonical correlation[J].Journal of Fuzhou University:Natural Sciences Edition,2004,32(4):438-441(in Chinese).