用户名: 密码: 验证码:
基于支持向量机的电力系统暂态稳定评估研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
电力系统暂态稳定评估(TSA)是关系到电力系统安全稳定运行的重要问题。论文结合模糊理论和集成学习对TSA问题进行了研究,主要研究内容如下:以IEEE 10机39节点新英格兰系统作为仿真对象,采用电力系统BPA软件进行暂态稳定仿真,构建用于评估的原始样本集;采用SVM算法进行暂态稳定评估,设计具体的算法流程。论文引入ROC曲线作为SVM训练参数选择的一种方法,并且引入更多的评估指标,更具说服力;针对SVM本身存在的训练缺陷,即对于样本的一视同仁,论文提出在SVM中加入模糊隶属度,形成模糊支持向量机(FSVM)进行TSA。在仿真过程中,采用K最近邻方法(K-NN)用于构建模糊隶属度,C++编程实现TSA。仿真结果显示,该方法在评估正确率上比SVM有了一定的提高;针对单一SVM的缺陷,论文提出采用AdaBoost算法,用于集成SVM学习。仿真得出评估结果,即该方法比上述任何一种方法都有更高的评估可靠性;论文对上述方法进行比较,证实论文提出的改进方法是有效的。
Power system transient stability assessment is one of the most important problems which relate power system secure-stable performance. The fuzzy theory and combination theory combined in dealing with TSA problem in this paper have been systematically studied in this paper, which includes: 10-machine-39 bus-New England system is simulated in this paper. First, Power system BPA software is used for transient stability simulation, thus the original data sets are formulated; SVM method is adopted in TSA, and the detailed algorithm flow is given. In this part, ROC curve used as a new method of SVM training parameter is proposed, and more assessment indexes are introduced, which conformed the results of the simulation; FSVM which apply a fuzzy membership to each input point of SVM and reformulating SVM into fuzzy SVM, is proposed for overcoming the limitation of SVM, that is SVM treats all the training points uniformly. So FSVM is proposed for dealing with TSA problem.Fisrt, K nearest method (K-NN) is applied to construct fuzzy membership. Then, the TSA results are given by C++ programming. The simulation results show that the accuaracy is improved; AdaBoost learning method is proposed for boosting the results of SVM. This method combines different SVMs, which overcomes the limitation of SVM. The simulation results are given and show that this method is the most effective in classification reliability; The above methods are compared. The results show that the improvement methods are effective in dealing with TSA problem.
引文
1 Prabha Kundur.电力系统稳定与控制.北京:中国电力出版社,2001
    2 鲍颜红,方勇杰,薛禹胜等.在线决策紧急控制系统中的若干问题.电力系统自动化,2001,25(24):1~2,16
    3 王恒,谢小荣,童陆园等.集中分层式安全稳定控制系统的开发及其在贵州电网中的应用.继电器,2005,33(2):75~78
    4 邹云.非常状态下应急控制稳定评估理论.江苏大学学报(自然科学版),2004,25(2):132~136
    5 李光琦.电力系统暂态分析.第二版.北京:中国电力出版社,1995
    6 吴政球,曾少钧.基于时域仿真的暂态稳定裕度及其灵敏度解析分析.电力系统及其自动化学报,2001,13(6):4~7,19
    7 Chan, K.W., Cheung, C.H., Su, H.T.. Time domain simulation based transient stability assessment and control. Power System Technology. Proceedings.PowerCon 2002.International Conference, 2002
    8 傅书逿,倪以信,薛禹胜.直接法稳定分析.北京:中国电力出版社,1999
    9 Hiromu Sakaguchi, Atsushi Ishigame, Shirou Suzaki. Transient stability assessment for power system via Lur' e type Lyapunov function, power systems conference and exposition IEEE PES. 2004
    10 刘笙,汪静.电力系统暂态稳定的能量函数分析.上海交通大学出版社,1996
    11 夏成军,胡会骏,何仰赞.在线暂态稳定评估的等效机暂态能量函数法.华中科技大学学报,2004,32(12):51~53
    12 Wan Rui, Chung, T.S., Fang, D.Z.. Trajectory stability assessment using NEF approach considering stability measures. IEEE Transanctions on power system, 2004, 2 (2): 740~745
    13 Luna-Lopez I, Canedo J.M., Loukianov A. Dynamical method for CUEP detection in power system transient stability assessment. Power Engineering Society Winter Meeting, 2002
    14 Lau Buon Sing, Wong Kit Po. Transient stability assessment:an artificial neural network approach. Neural networks. Proceedings, IEEE international conference, 1995
    15 Sobajic D J, Pao Y H. Artificial neural-net based dynamic security assessment for electric power systems. IEEE Transactions on power systems, 1989, 4 (1):220~228
    16 陶兰,江缉光.人工神经网络在电力系统暂态安全分析中的应用.清华大学学报(自然科学版),1994,34(4):62~68
    17 Edwards A R, Chan K W, Dunn R W, et al. Transient stability screening using artificial neural networks within a dynamic security assessment system. IEEE Proc.-Gener.Transm.Distrib, 1996, 143(2): 129~134
    18 Lo K L, Tsai R J Y. Power systems transient stability analysis by using modified Kohonen network. Proc.1995 IEEE Int.Conf.on neural networks, 2, Perth, Australia, 1995
    19 周伟,陈允平.自组织影射神经网络用于暂态稳定性分析的研究.电力系统自动化,2002,26(15):33~38
    20 S.K.Tso, X.RGu. Feature selection by separability assessment of input spaces for transient stability classification based on neural networks. Electrical power and energy systems. 2004 (26): 153~126
    21 顾雪平,张文朝.基于Tabu搜索技术的暂态稳定分类神经网络的输入特征选择.中国电机工程学报,2002,22(7):66~22
    22 于之虹,郭志忠.遗传算法在暂态稳定评估输入特征选择中的应用.继电器,2004,32(1):16~20
    23 张文朝,顾雪平,刘艳芳.Fisher识别用于暂态稳定评估的训练样本集压缩.华北电力大学学报,2002,29(3):44~47
    24 张琦,韩祯祥,曹绍杰,顾雪平.用于暂态稳定评估的人工神经网络输入空间压缩方法.电力系统自动化,2001,25(2):32~35,39
    25 李军,刘艳,顾雪平.基于信息熵的属性离散化算法在暂态稳定评估中的应用.电力系统自动化,2005,29(8):26~31
    26 于之虹,郭志忠.基于数据挖掘理论的电力系统暂态稳定评估.电力系统自动化,2003,27(8):45~48
    27 许涛,贺仁睦,王鹏,徐东杰.基于数据挖掘技术的电力系统暂态稳定预测.华北电力大学学报,2004,31(4):1~4
    28 许涛,贺仁睦,王鹏,徐东杰.基于统计学习理论的电力系统暂态稳定评估.中国电机工程学报,2003,23(11):51~55
    29 马骞,杨以涵,刘文颖等.多输入特征融合的组合支持向量机电力系统暂态稳定评估.中国电机工程学报,2005,25(6):18~23
    30 许涛,贺仁睦,王鹏,徐东杰.一种新的加速暂态稳定预测算法.继电器,2004,32(12):5~7
    31 仇向东.可视化电力系统分析及暂态稳定评估软件的开发:[学位论文],保定:华北电力大学,2001
    32 李卫东,唐艳丽.电力系统运行模式结构特征提取方法的研究.中国电力,1998,31(4):29~31
    33 张文朝.基于人工神经网络的暂态稳定评估技术的研究:[学位论文],保定:华北电力大学,2001
    34 倪以信,陈寿孙,张宝霖.动态电力系统的理论和分析.北京:清华大学出版社,2002
    35 马大强.电力系统机电暂态过程.水利电力出版社,2003
    36 白雪峰,倪以信.电力系统动态安全分析综述.电网技术,2004,28(16):14~20
    37 瓦普尼克.统计学习理论的本质.北京:清华大学出版社,2000
    38 Nello Cristianini,John Shawe-Taylor.支持向量机导论.北京:电子工业出版社,2004
    39 边肇祺,张学工.模式识别.第二版.北京:清华大学出版社,1999
    40 刘艳芳,顾雪平.基于支持向量机的电力系统暂态稳定分类研究.华北电力大学学报,2004,31(3):26~29,55
    41 L.S.Moulin, A.P.A.daSilva, M.A.EI-Sharkawi, R.J.MatksII. Support vector machines for transient stability analysis of large-scale power systems. IEEE Transactions on power systems. 2004, 2 (19):818~825
    42 L.S.Moulin, M.A.E1-Sharkawi. Support vector and multilayer perceptron neural networks applied to power systems transient stability analysis with input dimensionality reduction. Chicago:IEEE power engineering society summer meeting. 2002
    43 Xiaohong Wang, Sitao Wu, Qunzhan Li, Xiaoru Wang. v-SVM for transient stability assessment in power systems. Autonomous decentralized system, ISADS 2005.
    44 郑小霞,钱锋.高斯核支持向量机分类和模型参数选择研究.计算机工程与应用.2006(1):77~79
    45 J.L.Jardim. Online Dynamic Security Assessment: Implementation Problems and Potential Use of Artificial Intelligence. Power Engineering Society Summer Meeting, 2002
    46 严宇,刘天琪.基于神经网络和模糊理论的电力系统动态安全评估.四川大学学报,2004,36(1):106~110
    47 王守相,张伯明,郭琦.在线动态安全评估中事故扫描的综合性能指标法.电网 技术,2005,29(1):60~64
    48 Chadalavada V, Vittal V, Ejebe G C et al. An on-line contingency filtering scheme for dynamic security assessment. IEEE Transactions on Power System, 1997, 12 (1): 153~161
    49 李建民,张钹,林福宗.支持向量机的训练算法.清华大学学报.2003,43(1):120~124
    50 方学立,梁甸农,董臻.目标检测性能的定量评估方法.系统工程与电子技术.2005,27(12):1991~1993,2106
    51 Darrin C. Edwards, Charles E. Metz, Matthew A. Kupinski. Ideal observers and optimal ROC hypersurfaces in N-class classification. IEEE Transactions on Medicine imaging, 2004, 23(7): 891~895
    52 刘普寅,吴孟达.模糊理论及其应用.长沙:国防科技大学出版社,1998
    53 Chun-Fu Lin, Sheng-De Wang. Fuzzy Support Vector Machines. IEEE Transactions on neural networks, 2002, 13(2): 464~471
    54 杨志民,田英杰,邓乃扬.模糊支持向量分类机.计算机工程.2005,31(20):25~26,32
    55 Han-Pang Huang, Yi-Hung Liu. Fuzzy Support Vector Machines for Pattern Recognition and Data Mining. International Journal of Fuzzy System, 2002, 4 (3): 826~835
    56 Takuya Inoue, Shigeo Abe. Fuzzy Support Vector Machines for Pattern Classifiction. IEEE, 200(12): 1449~1454
    57 Norikazu Takahashi, Tetsuo Nishi. Rigorous Proof of Termination of SMO Algorithm for Support Vector Machines. IEEE Transactions on neural networks, 2005, 16 (3): 774~776
    58 赵洪波,赵丽红.支持向量机学习算法—序列最小优化(SMO).绍兴文理学院学报.2003,23(10):21~24
    59 颜辉.K-近邻法在入侵检测中的应用.吉林工程技术师范学院学报(工程技术报).2003,19(12):19~22
    60 黄晓斌,万建伟,张燕.一种改进的自适应K近邻聚类算法.计算机工程与应用.2004,(15):76~78,130
    61 马永军,李孝忠,王希雷.基于模糊支持向量机和核方法的目标检测方法研究.天津科技大学学报.2005,20(3):29~32
    62 Zhu.H, Basir.O. A K-NN associated fuzzy evidential reasoning classifier with adaptive neighbor selection. IEEE International Conference, 2001
    63 章学锋,石繁槐.FSVM在有限集脱机手写体汉字识别中的应用.计算机工程.2003,29(13):109~111
    64 朱志宇,张冰,刘维亭.基于模糊支持向量机的语音识别方法.计算机工程.2006,32(2):180~182
    65 许多,严洪森.基于模糊支持向量机的产品设计时间估计方法.中国机械工程.2005,16(6):533~537
    66 郑建军,甘仞初,贺跃,于同.神经网络分类器动态集成方法.北京理工大学学报.2005,25(12):1062~1065,1091
    67 魏玲,张文修.基于支持向量机集成的分类.计算机工程.2004,30(13):1~2,17
    68 王琳,冯正进,刘成良,崔光量.集成多分类器的人脸识别.计算机工程.2004,30(17):3~4,49
    69 邓慧琼,艾欣,刘昊.基于支持向量机的电力系统连锁故障评估方法研究.中国电机工程学报.2005,25(25):178~183
    70 沈学华,周志华,吴建鑫,陈兆乾.Boosting和Bagging综述.计算机工程与应用.2000,(12):31~32,40
    71 Robert E, Shapire. The boosting approach to machine learning: An overview. In MSRI Workshop on Nonlinear Estimation and Classification, 2002
    72 Harris Drucker. Improving Regression using Boosting Techniques. Proceedings of the Fourteenth International Conference on Machine Learning, 1997
    73 郭红刚,方敏.AdaBoost方法在入侵检测技术上的应用.计算机应用.2005,25(1):144~146
    74 D.P.Solomatine, D.L.Shrestha. AdaBoost.RT: a Boosting Algorithm for Regression Problems. IEEE, 2004(2):1163~1168

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700