基于自组织映射神经网络K-means聚类算法的风电场多机等值建模Multi-machine Equivalent Modeling of Wind Farms Using SOM-based K-means Clustering
赵凯,侯玉强
ZHAO Kai,HOU Yuqiang
摘要(Abstract)：
为研究高比例风电接入对电网安全稳定性的影响,提出了基于SOM(自组织映射神经网络) Kmeans聚类的风电场多机等值建模方法。首先选取风电场运行时的有功功率、无功功率、机端电压、输出电流、平均风速5种状态变量作为聚类算法的输入变量矩阵,通过基于SOM K-means聚类算法对变量矩阵进行处理,得到风电机组等值群数。然后用1台机组并联理想受控电流源的方法表征整个同群机组,得到风电机组的多机等值模型并进行仿真计算。最后通过与单机模型及详细模型在风速扰动和短路下的仿真曲线对比验证所提出的多机等值方法的有效性。
In order to study the impact of high proportion wind power integration on grid security and stability,a multi-machine equivalent modeling method for wind farm using SOM-based(self-organizing map) K-means clustering is proposed. In this paper, active power, reactive power, terminal voltage, output current and average wind speed are selected as input variable matrix; then the variable matrix is handled through SOMbased K-means clustering to conclude equivalent group number of wind turbines. The same group of wind generators are represented by an equivalent wind turbine through a wind generator paralleled with an ideal current source to conclude a multi-machine equivalent model and simulation. Through comparison of simulation curves of single-machine model and detailed model under wind speed disturbance and short-circuit fault,the multi-machine equivalent method is verified.
关键词(KeyWords)：
风电场;等值建模;SOM;K-means聚类
wind farms;equivalent modeling;self-organizing map;K-means clustering
基金项目(Foundation): 国家电网有限公司科技项目(52460817A047)
作者(Author):
赵凯,侯玉强
ZHAO Kai,HOU Yuqiang
DOI: 10.19585/j.zjdl.201908005
参考文献(References)：
- [1]郑可轲,牛玉广.大规模新能源发电基地出力特性研究[J].太阳能学报,2018,39(9):2591-2598.
- [2]安之,沈沉,郑泽天,等.考虑风电随机性的直驱风机风电场等值模型评价方法[J].中国电机工程学报,2018,38(22):6511-6519.
- [3]LI W X,CHAO P P,LIANG X D,et al.An Improved single-machine equivalent method of wind power plants by calibrating power recovery behaviors[J].IEEE Transactions on Power Systems,2018,33(4):4371-4381.
- [4]高澈,牛东晓,罗超,等.双馈风电场单机与多机等值模型对次同步振荡特性影响的对比[J].电力自动化设备,2018,38(8):152-157.
- [5]丁明,马彪,韩平平.用P-V分析法比较几种风电场静态等值建模[J].中国电力,2013,46(1):26-29.
- [6]晁璞璞,李卫星,金小明,等.基于有功响应的双馈型风电场实用化等值方法[J].中国电机工程学报,2018,38(6):1639-1646.
- [7]潘学萍,张弛,鞠平,等.风电场同调动态等值研究[J]电网技术,2015,39(3):621-628.
- [8]陈树勇,王聪,申洪,等.基于聚类算法的风电场动态等值[J].中国电机工程学报,2012,32(4):11-19.
- [9]吴琴,钟庆,王钢,等.基于模糊C均值聚类的风电场多机等值方法[J].现代电力,2016,33(6):27-32.
- [10]RZESZUTEK R,ANDROUTSOS D,KYAN M.Self-orga nizing maps for topic trend discovery[J].IEEE Signal Processing Letters,2010,17(6):607-610.
- [11]魏同发.基于SOM-BP的风机故障智能诊断[J].智慧工厂,2018(8):53-56.
- [12]SAHOO S K,MAKUR A.Dictionary training for sparse representation as generalization of K-Means clustering[J].IEEE Signal Processing Letters,2013,20(6):587-590.
- [13]王雁凌,马洪宇,成一平,等.基于支持向量回归和K均值聚类的降温负荷组合测算模型[J].现代电力,2019,36(3):51-57.
- [14]曹娜,于群.风速波动情况下并网风电场内风电机组分组方法[J].电力系统自动化,2012,36(2):42-46.
- [15]CHEN Z.Wind power in modern power systems[J].Journal of Modern Power Systems and Clean Energy,2013,1(1):2-13.
- [16]鞠平,吴峰,金宇清.可再生能源发电系统的建模与控制[M].北京:科学出版社,2014.
- [17]LI W X,CHAO P P,LIANG X D,et al.A practical equivalent method for DFIG wind farms[J].IEEE Transactions on Sustainable Energy,2018,9(2):610-620.
- [18]严干贵,李鸿博,穆刚,等.基于等效风速的风电场等值建模[J].东北电力大学学报,2011,31(3):13-19.
- [19]刘清华,赵岩.风电场的风机设备选择及运行维护的优化[J].渤海大学学报(自然科学版),2018,39(2):171-181.