摘要
基于最小二乘支持向量机理论,建立风速预测模型。同时,由于最小二乘支持向量机参数选取尚无有效方法,该文尝试采用蚁群算法理论来进行参数优化选择。选取某风场前四天的实测风速(采样间隔30min),应用所建立的风速预测模型,来预测第五天的48个风速值,其预测的平均绝对百分比误差仅为9.53%,预测效果较理想,验证了应用蚁群优化算法理论与最小二乘支持向量机理论进行风速预测的可行性,可为风电场规划选址和风力发电功率预测等提供理论支持。
This paper based on Least Squares Support Vector Machine theory to build the wind speed forecasting model. Meanwhile, as there is still no effective choice method of Least Squares Support Vector Machine parameter, this paper tried to use Ant Colony Algorithm theory to optimization choice for parameter. And last, use wind farm observed wind speed （sampling interval is 30 minutes） of the day before four days to forecast the 48ind wind speed of the fifth day through this paper＇s wind forecasting model, and prediction result is that the MAPE is only 9,53 %, the prediction effect is relative ideal, confirm the feasibility of applying the Ant Colony Optimization Algorithm and Least Squares Support Vector Machine theory to forecast the wind speed, it will provide theoretical support to wind farm layout and wind power forecasting and so on.
出处
《太阳能学报》
EI
CAS
CSCD
北大核心
2011年第3期296-300,共5页
Acta Energiae Solaris Sinica
关键词
风速预测
最小二乘支持向量机
蚁群优化算法
风电场
风力发电
wind speed forecasting
Least Squares Support Vector Machine
Ant Colony Optimization Mgorithm
wind farm
wind power
