Abstract:A wind speed forecasting model for wind farm based on support vector machine is proposed. Through wavelet decomposition and genetic algorithm, the data are preprocessed and the parameters are optimized. The model includes data processing unit, parameter optimization and support vector machine unit. The historical wind speed data is input to the model, and the model outputs the future wind speed data. Meanwhile, the adjustable parameters of the model is introduced, in order to improve the general adaptability for the different wind speed data. The simulation results show that the forecast wind speed is following the true value, what’s more, the model can adapt to different wind data.
[1] 陈树勇, 戴慧珠, 白晓民, 等. 风电场的发电可靠性模型及其应用[J]. 中国电机工程学报, 2000, 20(3): 26-29. [2] 孙春顺, 王耀南, 李欣然. 小时风速的向量自回归模型及应用[J]. 中国电机工程学报, 2008, 28(14): 112-117. [3] 潘迪夫, 刘辉, 李燕飞. 风电场风速短期多步预测改进算法[J]. 中国电机工程学报, 2008, 28(26): 87-91. [4] Damousis I G, Dokopoulos P. A fuzzy expert system for the forecasting of wind speed and power generation in wind farms[C]. IEEE Power Industry Computer Applications Conference, 2001. [5] Alexandre C, Antonio C, Jorge N, et al. A review on the young history of the wind power short-term prediction[J]. Renewable and Sustainable Energy Reviews, 2008(12): 1725-1744. [6] 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. [7] 王承煦, 张源. 风力发电[M]. 北京: 中国电力出版社, 2003. [8] 邓乃扬, 田英杰. 数据挖掘中的新方法—支持向量机[M]. 北京: 科学出版社, 2004. [9] Vapnik V. 统计学习理论的本质[M]. 张学工, 译. 北京: 清华大学出版社, 2000. [10] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1): 32-42. [11] 程正兴. 小波分析算法与应用[M]. 西安: 西安交通大学出版社, 1998. [12] Stephane G M. A theory for multiresolution signal decomposition: the wavelet representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674-693. [13] Mitchell R J, Chambers B, Anderson A P. Array pattern synthesis in the complex plane optimized by a genetic algorithm[J]. Electronics Letters, 1996, 32(20): 1843-1845. [14] 张文修, 梁怡. 遗传算法的教学基础[M]. 西安: 西安交通大学出版社, 2000. [15] 石钧. 多小波: 理论和应用[J]. 信号处理, 1999, 15(4): 25-27.