基于IDE-LSSVM的风电场短期风速预测

发布时间：2018-05-05 02:14

本文选题：风电场 + 短期风速预测　；参考：《系统仿真学报》2017年07期

【摘要】：为进一步提高风电场短期风速预测精度,提出一种改进的差分进化算法优化的最小二乘支持向量机短期风速预测模型。在改进的差分进化算法中综合了两种变异操作算子,改进了变异因子和交叉概率因子,使其根据进化代数自适应变化,保证了进化初期算法的全局搜索能力和种群多样性,提高了进化算法末期局部搜索精度和收敛速度。把改进的差分进化算法用于最小二乘支持向量机的参数寻优,提高了模型的预测精度,并在河北某风电场的真实历史数据集上建立风速预测模型,仿真实验验证了方法的有效性。
[Abstract]:In order to further improve the prediction accuracy of wind speed in short term in wind farm, an improved differential evolutionary algorithm is proposed to optimize the model of short-term wind speed prediction based on least squares support vector machine (LS-SVM). In the improved differential evolution algorithm, two kinds of mutation operators are integrated, and the mutation factor and the crossover probability factor are improved to make them adapt to the variation according to the evolutionary algebra, which ensures the global searching ability and population diversity of the initial evolutionary algorithm. The local search accuracy and convergence speed of the evolutionary algorithm are improved. The improved differential evolution algorithm is applied to the parameter optimization of the least square support vector machine (LS-SVM), and the prediction accuracy of the model is improved, and the wind speed prediction model is established on the real historical data set of a wind farm in Hebei Province. Simulation results show that the method is effective.
【作者单位】：华北电力大学自动化系;
【基金】：中央高校基本科研业务费专项资金(2014MS139)
【分类号】：TM614;TP18

【参考文献】