基于的V-支持向量机地风电场短期风速地概率预测.docVIP

PAGE 4 杨健维等：基于小波熵权和支持向量机的高压输电线路故障分类器 Vol. 31 No.0 实用标准文案 精彩文档 第31卷 第0期 电 网 技 术 Vol. 31 No.0 2007年0月 Power System Technology 000. 2007 文章编号：1000-3673（2007）08-0082-06 中图分类号：TM614 文献标识码：A 学科代码：480·6040 基于V－支持向量机的风电场短期风速的概率预测 杜 颖1，卢继平2，李 青3，邓颖玲4 （1.广东省电力设计研究院，广东省 广州市 510600；2．输配电装备及系统安全与新技术国家重点实验室(重庆大学)，重庆市 沙坪坝区 400044；3．甘肃洁源风电有限责任公司，甘肃省 兰州市 730050；4．中国民用航空湛江空中交通管理站，广东省 湛江市 524017） Wind Speed Probabilistic Forecasting of Wind Farm Based on V-Support Vector Regression Machine DU Ying1，LU Ji-ping2，LI Qing3，DENG Ying-ling4 （1.Guangdong electric power institute, Guangzhou 510600 Guangdong Province, China;2．State Key Laboratory of Power Transmission Equipment System Security and New Technology(Chongqing University)，Shapingba District，Chongqing 400044，China；3．Gansu Clean Source of Wind Power Co.,Ltd.，Lanzhou 730050，Gansu Province，China；4．China CIVIL Zhan Jiang Air Traffic Management Station，Zhanjiang 524017，Guangdong Province，China） ABSTRACT: A wind speed forecasting for wind farm based on v support vector regression machine is proposed. Taking historical wind speed data, atmospheric pressure and temperature as the input, the wind speed and environmental condition are trained by v-SVRM, then a forecasting model is built, and by selecting different parameters of the v, you can calculate the probability of the corresponding confidence intervals of wind speed. Forecasting wind speed by the proposed method, the obtained results are basically in accordance with the values of actual wind speed. Comparing the wind speeds forecasted by the proposed method with those forecasted by BP neural network based method, it is shown that the proposed method is better than the latter in robustness and forecasting accuracy. KEY WORDS: wind power generation；wind speed forecasting；least squares support vector machine ； grid search；BP neural network 摘要：提出了一种基于v－支持向量机的风电场风速的概率预测方法。以历史风速、气压、温度数据作为输入，对风速和环境条件进行训练，建立预测模型，并且运用网格搜索法确定模型参数，通过对参数v的不同选取，可以计算出相应概率下的风速置信区间。算例结果表明，使用上述方法预测的