基于相关向量机的故障后功角稳定分析

doi:10.16182/j.issn1004731x.joss.201808034

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (8): 3098-3104.doi: 10.16182/j.issn1004731x.joss.201808034

基于相关向量机的故障后功角稳定分析

李海英, 薛琢成

上海理工大学电气工程系,上海 200093

收稿日期:2016-10-21 出版日期:2018-08-10 发布日期:2019-01-08
作者简介:李海英(1975-),女,上海,博士,副教授,研究方向为大数据在智能电网中的应用;薛琢成(1993-),男,江苏,硕士,研究方向为电力系统优化运行。
基金资助:
国家自然科学基金(51207092)

Stability Analysis of Post-fault Power Angle Based on Relevance Vector Machine

Li Haiying, Xue Zhuocheng

Department of Electrical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2016-10-21 Online:2018-08-10 Published:2019-01-08

摘要/Abstract

摘要： 能源互联成为了当前研究的热点,随着大规模新能源接入电网,将会对电力系统的安全运行带来新的挑战。在线快速稳定性分析是解决这一问题的有效途径之一。传统的电力系统暂态安全分析方法已经难以适应当下在线应用,而大数据处理和机器学习的进一步发展为其提供了新的思路。采用基于贝叶斯框架的相关向量机(Relevance Vector Machine, RVM)的分类模型,设计一种功角分析策略,找出适当的采样点个数作为RVM的输入量,得到系统中各发电机功角关系从而判断出机组运行情况。在新英格兰10机39节点系统中验证并显示了较高的准确度。

关键词: 电力系统, 功角稳定, 暂态稳定, 相关向量机, 贝叶斯概率学习

Abstract: Energy interconnection has become a hot topic in the current research.With the large-scale of new energy into the grid, the safe operation of power system is facing new challenges. On line fast stability analysis is one of the effective ways to solve this problem. Traditional power system transient safety analysis method is difficult to adapt to the on-line analysis, and the further development of large data processing and machine learning provides a new way of thinking. The classification model of relevance vector machine (RVM) based on Bayesian framework is used to design a kind of power angle classification strategy.The appropriate number of sampling points is found as the input of RVM, and the generator angle relation of the system is gotten to determine the unit operation. The method is verified in the New England 10-machine 39-node system and the results show a high degree of accuracy.

Key words: power system, power angle stability, transient stability, relevance vector machine, Bayesian probability learning

中图分类号:

TM71

李海英, 薛琢成. 基于相关向量机的故障后功角稳定分析[J]. 系统仿真学报, 2018, 30(8): 3098-3104.

Li Haiying, Xue Zhuocheng. Stability Analysis of Post-fault Power Angle Based on Relevance Vector Machine[J]. Journal of System Simulation, 2018, 30(8): 3098-3104.

参考文献

[1] 蔡斌, 吴素农, 王诗明, 等. 电网在线安全稳定分析和预警系统[J]. 电网技术, 2007, 31(2): 36-41.
CAI Bin, WU Sunong, WANG Shiming, et al.Power Grid On-line Security and Stability Analysis and Forewarning System[J]. Power System Technology, 2007, 31(2): 36-41.
[2] Park D C, Elsharkawi M A, Marks R J I, et al. Electric load forecasting using an artificial neural network[C]// IEEE PES 1990 Summer Meeting, 1991: 442-449.
[3] 顾雪平, 曹绍杰, 张文勤. 基于神经网络暂态稳定评估方法的一种新思路[J]. 中国电机工程学报, 2000, 20(4): 77-82.
GU Xueping, CAO Shaojie, ZHANG Wenqin.A NEW FRAMEWORK FOR TRANSIENT STABILITY ASSESSMENT BASED ON NEURAL NETWORKS[J]. Proceedings of the Csee, 2000, 20(4): 77-82.
[4] El-Sharkawi M A, Huang S J. Development of genetic algorithm embedded Kohonen neural network for dynamic security assessment[C]//International Conference on Intelligent Systems Applications To Power Systems, 1996. Proceedings, Isap. IEEE, 1996: 44-49.
[5] 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[J]. 电力系统保护与控制, 2004, 32(1): 16-20.
YU Zhihong, GUO Zhizhong.Feature selection based on genetic algorithm for transient stability assessment[J]. Relay, 2004, 32(1): 16-20.
[6] Mohammadi M, Gharehpetian G B.Power System On-Line Static Security Assessment by Using Multi- Class Support Vector Machines[J]. Journal of Applied Sciences (S0255-8297), 2008, 8(12).
[7] Kalyani S, Swarup K S.Support vector machine based pattern recognition approach for static security assessment[J]. International Journal of Artificial Intelligence (S0004-3702), 2010, 5(10): 17-36.
[8] 马骞, 杨以涵, 刘文颖, 等. 多输入特征融合的组合SVM电力系统暂态稳定评估[J]. 中国电机工程学报, 2005, 25(6): 17-23.
MA Qian, YANG Yihan, LIU Wenying, et al.POWER SYSTEM TRANSIENT STABILITYASSESSMENT WITH COMBINED SVM METHOD MIXING MULTIPLE INPUT FEATURES[J]. Zhongguo Dianji Gongcheng Xuebao/proceedings of the Chinese Society of Electrical Engineering, 2005, 25(6): 17-23.
[9] Wang X, Ye M, Duanmu C J.Classification of data from electronic nose using relevance vector machines[J]. Sensors & Actuators B Chemical (S0925-4005), 2009, 140(1): 143-148.
[10] Widodo A, Yang B S.Application of relevance vector machine and survival probability to machine degradation assessment[J]. Expert Systems with Applications (S0957-4174), 2011, 38(3): 2592-2599.
[11] 段青. 基于稀疏贝叶斯学习方法的回归与分类在电力系统中的预测研究[D]. 济南: 山东大学, 2010.
DUAN Qing.Study of Forecasting in Power Systems with Regression and Classification Based on Sparsity Bayesian Learning[D]. Ji’nan: Shandong University, 2010.
[12] Salman S K, Teo A L J. Investigation into the estimation of the critical clearing time of a grid connected wind power based embedded generator[C]//Transmission and Distribution Conference and Exhibition 2002: Asia Pacific. IEEE/PES. 2002: 975-980.
[13] 邵雅宁, 唐飞, 刘涤尘, 等. 一种适用于WAMS量测数据的系统暂态功角稳定评估方法[J]. 电力系统保护与控制, 2015, 43(6): 33-39.
SHAO Yaning, TANG Fei, LIU Dichen, et al.An approach of transient angle stability assessment in power system for WAMS measured data[J]. Power System Protection & Control, 2015, 43(6): 33-39.
[14] 李大虎, 曹一家. 基于PMU和混合支持向量机网络的电力系统暂态稳定性分析[J]. 电网技术, 2006, 30(9): 46-52.
LI Dahu, CAO Yijia.Power System Transient Stability Analysis Based on PMU and Hybrid Support Vector Machine[J]. Power System Technology, 2006, 30(9): 46-52.
[15] 李海英, 刘中银, 宋建成. 电力系统静态安全状态实时感知的相关向量机法[J]. 中国电机工程学报, 2015, 35(2): 294-301.
LI Haiying, LIU Zhongyin, SONG Jiancheng.Real-time Static Security Situational Awareness of Power Systems Based on Relevance Vector Machine[J]. Proceedings of the Csee, 2015, 35(2): 294-301.
[16] Guindon S, Gascuel O.PhyML—A simple, fast, and accurate algorithm to estimate large phylogenies by maximum likelihood[J]. Systematic Biology (S1063-5157), 2003, 52(5): 696-704.
[17] Burden F R, And M G F, Whitley D C, et al. Use of Automatic Relevance Determination in QSAR Studies Using Bayesian Neural Networks[J]. Journal of Chemical Information & Computer Sciences(S0095-2338), 2000, 40(6): 1423-1430.
[18] Tipping M.Relevance vector machine: US, US 6633857 B1[P]. 2003.
[19] Processor O, Matlab T, Introduction P.Power System Analysis Toolbox[K]. Tailieu Vn.
[20] Wong T T.Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation[J]. Pattern Recognition(S0031-3203), 2015, 48(9): 2839-2846.

基于相关向量机的故障后功角稳定分析

Stability Analysis of Post-fault Power Angle Based on Relevance Vector Machine

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	胡小曼, 王艳, 纪志成. 模糊信息粒化与改进RVM的滚动轴承寿命预测[J]. 系统仿真学报, 2021, 33(11): 2561-2571.
[2]	董伟杰, 黄民, 何国庆, 鲍威, 王义龙, 刘泉. 交直流混合电力系统机电电磁暂态稳定仿真系统[J]. 系统仿真学报, 2021, 33(11): 2711-2719.
[3]	张朝龙, 何怡刚, 袁莉芬. 基于CPSO-RVM的锂电池剩余寿命预测方法[J]. 系统仿真学报, 2018, 30(5): 1935-1940.
[4]	王唯一, 肖磊, 林德俊. 海洋钻井平台发电机组的仿真研究[J]. 系统仿真学报, 2018, 30(2): 664-671.
[5]	张亚男, 杨慧中. 基于RVM组合核优化的软测量模型研究[J]. 系统仿真学报, 2018, 30(1): 272-277.
[6]	黄松, 王艳, 纪志成. 多信息特征粒子群优化算法的动态经济负荷分配[J]. 系统仿真学报, 2017, 29(9): 2159-2167.
[7]	于淼, 尚伟鹏, 卢宁. 基于直接神经动态规划的电力系统协调控制[J]. 系统仿真学报, 2017, 29(4): 699-707.
[8]	贺智, 聂志成, 秦怡宁, 樊友平. 基于拉格朗日乘子和测量残差的参数辨识[J]. 系统仿真学报, 2017, 29(12): 2964-2971.
[9]	闫茹, 费敏锐, 杜大军. 针对电力系统蓄意攻击的简要技术分析[J]. 系统仿真学报, 2017, 29(10): 2507-2517.
[10]	牛玉广, 杨巍, 李晓明, 王世林, 林忠伟. 双馈风机神经电力系统稳定器设计与仿真研究[J]. 系统仿真学报, 2017, 29(1): 162-169.
[11]	牛玉广, 李晓明, 王世林, 林忠伟. 分散协调控制在风火混合电力系统中仿真研究[J]. 系统仿真学报, 2015, 27(3): 609-619.