基于WRF和SVM方法的风电场功率预报技术研究  

Study on Wind Power Forecasting of Wind Farm Based on WRF and SVM

作　　者：丁煌[1,2] 陶树旺[2] 肖子牛[3] 程兴宏[2] 

机构地区：[1]南京信息工程大学大气科学学院,江苏南京210044 [2]中国气象局公共气象服务中心,北京100081 [3]中国气象局气象干部培训学院,北京100081

出　　处：《高原气象》2013年第2期581-587,共7页Plateau Meteorology

基　　金：国家高技术研究发展计划(863计划)课题"风电场发电量短期预报技术研究"(2007AA05Z425);公益性行业(气象)科研专项"复杂地形风能预报技术研究"(GYHY201006035)共同资助

摘　　要：利用WRF(Weather Research and Forecasting)模式,对2006年河北省张北地区某风电场区域全年回报的风速和风向,以及与对应时间段70m高度的测风塔实测资料进行了对比分析,发现模式预报效果较好。利用2008年全年风电场每台风机的实际功率与对应时刻轮毂高度风速、风向、气温、相对湿度和气压回报资料,使用支持向量机(Support Vector Machine,SVM)回归方法建立了每台风机10min一次的风电场功率预报模型,并利用该模型进行了2009年为期一年的预报试验,检验模型的预报性能。结果表明,集WRF模式和SVM方法建立的风电功率预报方法具有较好的预报效果。各月预报相关系数在0.71～0.82之间,归一化均方根误差在9.8%～16.5%之间,归一化平均绝对误差在5.4%～10.5%之间;全年预报相关系数为0.79,归一化均方根误差为13.3%,归一化平均绝对误差为8.3%。Based on WRF（Weather Research and Forecasting Model） and SVM（Support Vector Ma- chine） regression method, short-term wind power forecast system was established. In order to verify the accuracy of WRF, wind speed and wind direction in a wind farm of Zhangbei region in 2006 were hindcasted by WRF model, which were used to compare with the observed data of wind tower at 70 m height. The verification was satisfactory. Wind power forecast model of every 10 rain for 30 wind turbines using SVM regression method were developed based on actual wind power recorded data and wind speed, wind direction, atmospheric temperature, relative humidity and atmospheric pressure values which hindcasted by WRF at 70 m height in 2008. For the assessing the forecasting effect of this wind power forecast model, forecasting experiments in 2009 were carried out. The results show that the method to combine WRF model with the SVM method to establish a wind power forecasting produce good prediction results, correlation coefficients ranged from 0.71 to 0.82, normalized root mean square error ranged from 9.8% to 16.5%, and normalized mean absolute error was between 5.4% and 10.5%. The whole yearls correlation coefficient is 0. 79, normalized root mean square error is 13.3%, and normalized mean absolute error is 8.3%

关 键 词：支持向量机 WRF模式 风电功率预报 

分 类 号：P425.6[天文地球—大气科学及气象学]