中文摘要：

为了减小风力发电的随机性对电力系统的影响,提出了一种基于最小二乘支持向量机的风功率短期预测模型.在研究最小二乘支持向量机的基础上,为解决最小二乘支持向量机建模时其参数对预测性能影响,运用粒子群算法对参数进行优化,最后建立了基于粒子群优化最小二乘支持向量机的预测模型.运用某风电场的实测数据进行仿真研究,为了对比分析,同时利用Elman神经网络模型和支持向量机模型进行了预测,仿真结果表明,本文所提方法与其它方法相比预测精度更高,可以有效地应用于风功率的预测.

英文摘要：

n order to reduce the influence of randomness of wind power generation on power system,this paper proposes a least squares support vector machine （LSSVM）based short-term wind power forecasting model,uses particle swarm optimization（PSO）to optimize the parameters aiming at the influence of LSSVM model parameters on prediction performance,and establishes the PSO-LSSVM based wind power prediction model.The simulation is carried out according to the actual data of a wind farm by using the model established in the paper,Elman neural network model and SVM model.The results show that the proposed method is of high prediction accuracy comparing with the other two methods.