大型风电场动态等值的改进支持向量聚类算法

滕卫军 1; 王锡凡 1; 石文辉 2

doi:10.7652/xjtuxb201505015

您当前的位置：

首页 >

文章列表页 >

大型风电场动态等值的改进支持向量聚类算法

更新时间：2025-07-09

- 大型风电场动态等值的改进支持向量聚类算法
- An Improved Support Vector Clustering Algorithm for the Dynamic Equivalence of Large Wind Farms
- 西安交通大学学报 2015年49卷第5期页码：94-99+115
- 作者机构：
  
  西安交通大学电气工程学院,西安,710049
- 作者简介：
- 基金信息：
  
  : 2014-09-19。作者简介: 滕卫军(1987—),男,博士生;王锡凡(通信作者),男,教授,博士生导师,中国科学院院士。基金项目: 国家电网公司科技资助项目(NY71-13-008)
- DOI：10.7652/xjtuxb201505015
  中图分类号： TH-39
- 网络首发：2015-05-10，
  
  纸质出版：2015
- 稿件说明：
移动端阅览
滕卫军 1, 王锡凡 1, 石文辉 2. 大型风电场动态等值的改进支持向量聚类算法[J]. 西安交通大学学报, 2015,49(5):94-99+115.

An Improved Support Vector Clustering Algorithm for the Dynamic Equivalence of Large Wind Farms[J]. 2015, 49(5): 94-99+115.
滕卫军 1, 王锡凡 1, 石文辉 2. 大型风电场动态等值的改进支持向量聚类算法[J]. 西安交通大学学报, 2015,49(5):94-99+115. DOI： 10.7652/xjtuxb201505015.

An Improved Support Vector Clustering Algorithm for the Dynamic Equivalence of Large Wind Farms[J]. 2015, 49(5): 94-99+115. DOI： 10.7652/xjtuxb201505015.

摘要

针对风速波动性强与风电场多样性导致的风机聚类参数多样化的特点

提出了一种基于支持向量聚类(SVC)的大型风电场动态等值聚类算法。该算法应用遗传算法实现簇标定

采用分段多目标函数迭代求解

保证了聚类结果的精度与速度

克服了传统SVC簇标定抽样判决的不足。应用样本轮廓值修正聚类结果

保证聚类结果的合理性

根据等值前后风机机端电压不变原则建立了电缆等值模型。以实际风电场为算例进行仿真

结果表明

该算法单次聚类时间为SVC的4%左右

采用遗传算法能够实现不同精度的等值机台数优化

得到的等值机与簇内单机的有功功率、无功功率动态特性具有较高一致性

轮廓值修正能够保证聚类结果的样本轮廓值都大于0。

Abstract

A clustering algorithm to the dynamic equivalent of large wind farms based on SVC is proposed to deal with the diversity of clustering parameter of wind turbines due to the variant of wind energies and the diversity of layout of wind farms. A genetic algorithm is used to realize clustering assignments. Piecewise multi-objective functions are used for iterative solution to ensure the speed and accuracy of clustering results

and to overcomes the disadvantage of traditional SVCs in clustering assignments. Outlier values of samples are used to modify the clustering results and to ensure the rationality of clustering results. An equivalent model for cables is built based on the principle that the terminal voltage of wind turbines keeps unchanged. Simulation results of a real wind farm show that the clustering time of the proposed method is about 4%of SVC. The proposed clustering method based on GA optimizes the number of equivalent wind turbines under different accuracies. The dynamic characteristics such as active power and reactive power of equivalent wind turbines are highly consistent with those of individual wind turbines in the cluster. Modification using outlier values ensures that all the outlier values of wind turbines are greater than 0.

关键词

Keywords

references

AHMAD S D, MAHMUD F F. A reliability model of large wind farms for power system adequacy studies [J]. IEEE Trans on Energy Conversion, 2009, 24(3): 792-801.

FERNANDEZ L M, GARCIA C A, SAENZ J R, et al. Equivalent models of wind farms by using aggregated wind turbines and equivalent winds [J]. Energy Conversion and Management, 2009, 50(3): 691-704.

MUHAMMAND A, ILIE I S, MILANOVIC J V, et al. Wind farm model aggregation using probabilistic clustering [J]. IEEE Trans on Power Systems, 2013, 28(1): 309-316.

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.

CEHN Shuyong, WANG Cong, SHEN Hong, et al. Dynamic equivalence for wind farms based on clustering algorithm [J]. Proceedings of the CSEE, 2012, 32(4): 11-19.

TRUDNOWSKI D J, GENTILE A, KHAN J M, et al. Fixed-speed wind-generator and wind-park modeling for transient stability studies [J]. IEEE Trans on Power Systems, 2004, 19(4): 1911-1917.

CHOWDHURY M A, SHEN W X, HOSSEINZADEH N, et al. A novel aggregated DFIG wind farm model using mechanical torque compensating factor [J]. Energy Conversion and Management, 2013, 67(3): 265-274.

FERNANDEZ L M, SAENZ J R, JURADO F. Dynamic models of wind farms with fixed speed wind turbines [J]. Renewable Energy, 2006, 31(8): 1203-1230.

FERNANDEZ L M, JURADO F, SAENZ J R. Aggregated dynamic model for wind farms with doubly fed induction generator wind turbines [J]. Renewable Energy, 2008, 33(1): 129-140.

LI H, YANG C, ZHAO B, et al. Aggregated models and transient performances of a mixed wind farm with different wind turbine generator systems [J]. Electric Power Systems Research, 2012, 92(11): 1-10.

AKHMATOV V, KNUDSEN H. An aggregate model of a grid-connected, large-scale, offshore wind farm for power stability investigations: importance of windmill mechanical system [J]. Electrical Power and Energy Systems, 2002, 24(9): 709-717.

HE Yikang, HU Jiabing, ZHAO Rende. Modeling and control of wind-turbine used DFIG under network fault condition [C]∥Proceedings of the 8th International Conference on Electrical and Systems. Piscataway, NJ, USA: IEEE, 2005: 986-991.

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.

CAO Na, YU Qun. A grouping method for wind turbines in a grid-connected wind farm during wind speed fluctuation [J]. Automation of Electric Power System, 2012, 36(2): 42-46.

ALI M, MATEVOSYAN J, MILANOVIC J V, et al. Effect of wake consideration on estimated cost of wind energy curtailments [C]∥8th International Workshop on Large Scale Integration of Wind Power into Power Systems as Well as on Transmission Networks for Offshore Wind Farms. Bremen, Germany: Wind Integration Workshop, 2009: 14-15.

曹娜, 赵海翔, 任普春, 等. 风电场动态分析中风速模型的建立及应用 [J]. 中国电机工程学报, 2007, 27(36): 68-72.

CAO Na, ZHAO Haixiang, REN Puchun, et al. Establish and application of wind speed model in wind farm dynamic analysis [J]. Proceedings of the CSEE, 2007, 27(36): 68-72.

TOMMASI L D, GIBESCU M, BRAND A J. A dynamic wind farm aggregate model for the simulation of power fluctuation due to wind turbulence [J]. Journal of Computational Science, 2010(1): 75-81.

米增强, 苏勋文, 杨奇逊, 等. 风电场动态等值模型的多机表征方法 [J]. 电工技术学报, 2010, 25(5): 162-169.

MI Zengqiang, SU Xunwen, YANG Qixun, et al. Multi-machine representation method for dynamic equivalent model of wind farms [J]. Transactions of China Electrotechnical Society, 2010, 25(5): 162-169.

HUR A B, HORN D, SIEGELMANN H T, et al. Support vector clustering [J]. Journal of Machine Learning Research, 2001(2): 125-137.

LEE J, Lee D. An improved cluster labeling method for support vector clustering [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(3): 461-464.

CHIANG J H, HAO P Y. A new kernel-based fuzzy clustering approach: support vector clustering with cell growing [J]. IEEE Transactions on Fuzzy Systems, 2003, 11(4): 518-527.

YANG J H, ESTIVILL-CASTRO V, CHALUP S K. Support vector clustering through proximity graph modeling [C]∥Proceedings of the 9th International Conference on Neural Information Processing. Piscataway, NJ, USA: IEEE, 2002: 552-559.

LEE S H, DANIELS K M. Cone cluster labeling for support vector clustering [C]∥ Proceedings of 6th SIAM Conference on Data Mining. Philadelphia, USA: SIAM, 2006: 151-162.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

氘氘中子源超热中子场优化设计

石化设备故障率分布参数和维修效果参数估计

基于遗传算法的复合式贴片机贴装过程优化

面向Pareto最优遗传算法的服务组合方法