基于信息粒化和支持向量机的风功率预测  

Wind Power Prediction Based on Information Granulation and Support Vector Machine

作　　者：吴康[1] 姚秀萍[2] 王维庆[1] 王海云[1] 李猛[1] 

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830047 [2]新疆电力公司,新疆乌鲁木齐830002

出　　处：《水力发电》2014年第5期81-83,共3页Water Power

基　　金：国家自然科学基金项目(51267017);教育部创新团队项目(IRT1285);自治区重大攻关项目(201230115-3)

摘　　要：基于信息粒化和支持向量机对大型风电场的输出功率进行短期预测,利用国内某大型风电场的实测输出功率数据进行回归预测模型的构建,应用结果表明:小样本情况下有效克服了传统的时间序列模型仅是单一线性模型的缺点,该方法可以有效的预测大型风电场的输出功率变化范围。Based on information granulation and support vector machines, the short-term power output prediction of large-scale wind farm is studied, and the regression prediction model of power output is built by using the measured data of a large domestic wind farm. The results show that the disadvantages of traditional time-series model which is only single linear model are effectively overcame in the case of small samples. This method can effectively predict the power output range of large wind farms.

关 键 词：信息粒化 支持向量机 功率预测 风电场 

分 类 号：TK81[动力工程及工程热物理—流体机械及工程]