基于运行数据和支持向量机的风电场动态建模

Wind farm modeling based on running data and SVM algorithm

风电场建模是研究风电并网技术的基础,找到一种能够精确反映风电场状态和大幅缩短仿真时间的模型是目前国内外学者的研究重点。文章基于统计学习理论的支持向量机算法,以风电场动态建模为目标,针对单机模型和K-means模型所产生的误差,提出一种基于风电场风速威布尔分布的支持向量机算法模型,并且利用实测数据和MATLAB/Simulink软件对算例进行仿真,风电场的有功功率和无功功率误差结果验证了该模型具有良好的动态性能,并且有效缩短了仿真时间。

Wind farm modeling is the basis of the research of wind power grid connected technology,it is the focus of scholars at home and abroad to find a model which can accurately reflect the state of the wind farm and shorten the simulation time. Proposing a concept for dynamic aggregate modeling of wind farms based on the support vector machine algorithm in the statistical theory and the Weibull distribution to replace the single-unit model and the K-means model which brought errors of active power and reactive power. The errs of active power and reactive power in wind farm show that model has good dynamic performance by applying the measured data and MATLAB/Simulink to simulate the case.