摘要
提出了一种基于粒子群(PSO)算法优化最小二乘支持向量机(LS-SVM)的风电场风速预测方法。以相关性较高的历史风速序列作为输入,建立预测模型,并用粒子群算法优化模型参数。在对未来1 h风速进行预测时,文章所提出的模型比最小二乘支持向量机模型及BP神经网络模型具有较高的预测精度和运算速度。算例结果表明,经粒子群优化的最小二乘支持向量机算法是进行短期风速预测的有效方法。
A wind speed forecasting for wind farm based on least squares support vector machine optimized by particle swarm optimization algorithm is proposed. Taking historical wind speed data which have higher correlation as the input, then a forecasting model is built, and by use of particle swarm optimization, the parameters of the model are determined. In the one hour wind speed forecasting of this wind farm ,the proposed wind speed model is compared with wind speed model based on least squares support vector machine （LS-SVM） and that based on back propagation neural network, the comparison results show that the proposed wind speed predicting model is better than these two models in both prediction accuracy and computing speed. The simulation results show that the least squares support vector machine optimized by particle swarm optimization algorithm is an effective method for short-term wind forecasting.
出处
《可再生能源》
CAS
北大核心
2011年第2期22-27,共6页
Renewable Energy Resources
基金
江苏省科技厅工业科技支撑计划项目(BE2009166)
关键词
风速预测
粒子群优化
最小二乘支持向量机
神经网络
wind speed forecasting
particle swarm optimization （PSO）
least squares support vector machine（LS-SVM）
neural network
