基于PSO优化LSSVM的短期风速预测

摘要

为了提高风电场风速短期预测的精确性,提出了基于粒子群算法优化最小二乘支持向量机的预测方法.首先求出风速时间序列的嵌入维数和延迟时间,进而对混沌风速时间序列进行相空间重构.利用粒子群算法对最小二乘支持向量机进行参数优化,然后利用优化后的最小二乘支持向量机模型对相空间重构后的风速时间序列进行预测,预测结果表明基于粒子群优化的最小二乘支持向量机的预测效果满足了精度要求.同时运用了支持向量机和BP神经网络模型进行预测,仿真结果表明,基于粒子群优化的最小二乘支持向量机预测方法具有预测精度高,预测速度快的优点,因此具有很高的工程实际应用意义.%In order to improve the accuracy of short-term wind speed forecast, this paper proposes a least squares support vector machine (LSSVM) model optimized by the particle swarm optimization (PSO). The phase space of the chaotic wind speed time series is reconstructed by calculating the embedding dimension and the delay time of the wind speed time series. The PSO is used to optimize the parameters of the LSSVM. Then the improved LSSVM model can be used to forecast the wind speed. The results show the improved LSSVM can meet the accuracy requirements. At the same time, this paper uses the SVM prediction model and the BP neural network prediction model to forecast the wind speed time series. The simulation results show that the PSO-LSSVM prediction model is more efficient and accurate. So it can be widely used in engineering practice.