基于高斯混合模型的风电场群功率波动概率密度分布函数研究  

Probability Density Distribution Function of Wind Power Fluctuation of A Wind Farm Group Based on the Gaussian Mixture Model

作　　者：崔杨[1] 杨海威[1] 李鸿博[2] 

机构地区：[1]东北电力大学电气工程学院,吉林省吉林市132012 [2]国网吉林省电力有限公司培训中心,吉林省长春市130022

出　　处：《电网技术》2016年第4期1107-1112,共6页Power System Technology

基　　金：国家重点基础研究发展计划项目(973项目)(2013CB228201);国家自然科学基金项目(51207018);国家电网公司科技项目(SGLNSY00FZJS1500191)~~

摘　　要：如何描述风电功率波动的概率密度分布特性一直是风电联网运行分析领域的难点。在利用概率密度函数法分析风电功率波动特性的基础上,首先验证了采用多种单一分布函数模型拟合风电波动概率密度分布特性的效果较差,并根据列维定理揭示了风电场群出力波动概率密度分布特性呈现多种分布的规律;在此基础上提出采用高斯混合模型替代单一分布函数模型来拟合风电波动概率密度分布特性的方法。仿真结果表明,高斯混合模型具有良好的拟合效果,适用于描述大型风电场群出力波动的概率密度分布特性。Description of probability density distribution characteristics of wind power fluctuation is always a challenge in grid-connected wind power operation analysis. Firstly, on basis of wind power fluctuation analysis with probability density functions, this paper verified unsatisfactory effects in fitting probability density distribution of wind power output fluctuation with single distribution function model. Then, diversity of probability density distribution of wind power output fluctuations was demonstrated according to Levy theorem. Therefore, this paper proposed to use Gaussian Mixture Model to fit probability density distribution instead of single distribution function model. Simulation results proved its good fitting effect and applicability in large-scale wind farms.

关 键 词：风电功率波动 概率密度分布 拟合效果 单一分布函数模型 高斯混合模型 

分 类 号：TM711[电气工程—电力系统及自动化]