基于谱聚类的城市低电压分区治理决策

doi:10.11930/j.issn.1004-9649.2016.10.101.05

摘要/Abstract

摘要： 在目前配电系统相对发输电系统较为落后的电力市场环境下，低电压治理是亟须解决的问题。合理地确定治理分区是科学、有效地进行低电压治理的重要前提。基于谱聚类算法的城市低电压分区方法，首先考虑了最低电压幅值、低电压涉及户数、电压越（下）限时间及年供电量4个指标构成样本空间。其次通过欧氏距离建立拉普拉斯（Laplace）矩阵，由Laplace矩阵的相对特征值差自动确定低电压治理的分区数目，将Laplace矩阵的前两个和前三个特征向量映射到二维和三维空间，直观地划分治理分区。然后构造评估函数，评估低电压分区的效果，采用k-means算法对特征向量进行聚类，画出分区谱系图，得到层次分明的低电压分区治理方案。该算法基于复杂网络原理，具有严谨的理论依据。以江西省某市典型数据为例验证了所提算法的有效性。

关键词: 配电系统, 谱聚类, 多因素, 低电压, 分区, 拉普拉斯矩阵

Abstract: The governance decision making of low voltage in urban power system, while the distribution system is relatively lagging than transmission system in the power market environment, is in dire need of solving. The partition of governance is very important premise of governance decision-making of low voltage. A partition method based on spectral clustering algorithm is proposed. Firstly, sample space is established with consideration of minimum voltage amplitude, number of low voltage customer count, voltage over-limitation time and annual power supply. Secondly, Laplace matrix is built by Euclidean distance. The relative differences of eigenvalues of similarity matrix is selected automatically to determine partition number. The first two and three eigen vectors are mapped to 2d and 3d spaces which provide intuitive guidance for partition. Then evaluation function is constructed to evaluate partition effectiveness. When partition effect is acceptable, k-means algorithm is used to cluster feature vector, obtain partition spectrum diagram and structured partition scheme. The proposed algorithm is based on complex network theory and has rigorous theoretical basis. Finally, the effectiveness of proposed algorithm is verified by simulation results of a Power Grid of Jiangxi province.

Key words: distribution system, spectral clustering, multivariate, low voltage, partition, Laplacian matrix

中图分类号:

TM715

张忠会，刘故帅，谢义苗，何乐彰. 基于谱聚类的城市低电压分区治理决策[J]. 中国电力, 2016, 49(10): 101-105.

ZHANG Zhonghui, LIU Gushuai, XIE Yimiao, HE Lezhang. Treatment Decision-Making of Partition in Low Voltage Based on Spectral Clustering in Urban Power System[J]. Electric Power, 2016, 49(10): 101-105.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.2016.10.101.05

https://www.electricpower.com.cn/CN/Y2016/V49/I10/101

参考文献

[1] 肖世杰. 电网安全稳定控制应用技术[M]．北京：中国电力出版社，2011：53-54．
[2] 徐振，谭甜源，乐健，等．农网末端低电压问题补偿方案研究[J]．电气应用，2013，32（9）：50-53．
XU Zhen, TAN Tianyuan, LE Jian, et al． The research of the low voltage compensation scheme for the end of rural power grid [J]．Electro-technical Application, 2013, 32(9): 50-53．
[3] 许刚，王紫雷．基于Normal矩阵谱平分法的快速电压控制分区[J]．电网技术，2014，38（1）：199-204．
XU Gang, WANG Zilei． Fast voltage control partitioning based on normal matrix spectral bisection method[J]． Power System Technology, 2014, 38(1): 199-204．
[4] 陈厚合，运奕竹，邢文洋，等．基于聚类分析方法的电力系统负荷节点分区策略[J]．电力系统保护与控制，2013，41（12）：47-53．
CHEN Houhe, YUN Yizhu, XING Wenyang, et al． A novel strategy of network partitioning for load node in power systems using spectral clustering [J]． Power System Protection and Control, 2013, 41(12): 47-53．
[5] 王金丽，盛万兴，宋祺鹏，等．配电网电能质量智能监控与治理仿真[J]．电网技术，2014，38（2）：515-519．
WANG Jinli, SHENG Wanxing, SONG Qipeng, et al． Research on intelligent power quality monitoring and on-line simulation for distribution network[J]． Power System Technology, 2014, 38(2):515-519．
[6] 赵莉，候兴哲，胡君，等．基于改进k-means算法的海量智能用电数据分析[J]．电网技术，2014，38（10）：2715-2720．
ZHAO Li, HOU Xingzhe, HU Jun, et al． Improved k-means algorithm based analysis on massive data of intelligent power utilization [J]． Power System Technology, 2014, 38(10): 2715-2720．
[7] 梁海平，顾雪平. 基于谱聚类的黑启动子系统划分[J]．电网技术，2013，37（2）：372-377．
LIANG Haiping, GU Xueping． Black-start network partitioning based on spectral clustering[J]． Power System Technology, 2013, 37(2): 372-377．
[8] SANCHEZ-GARCIA R J, FENNELLY M, NORRIS S, et al．Hierarchical spectral clustering of power grids [J]． IEEE Trans on Power Systems, 2014, 29(5): 2229-2237．
[9] 熊虎岗，程浩忠，孔涛．基于免疫—中心点聚类算法的无功电压控制分区[J]．电力系统自动化，2007，31（2）：22-26．
XIONG Hugang, CHENG Haozhong, KONG Tao． Network partitioning for reactive power voltage control based on immune-central point clustering algorithm[J]． Automation of Electric Power Systems, 2007, 31(2): 22-26．
[10] 曹一家．大电网安全性评估的系统复杂性理论[M]．北京：清华大学出版社，2010：28-29．
[11] 蔡泽祥，王星华，任晓娜．复杂网络理论及其在电力系统中的应用研究综述[J]．电网技术，2012，36（11）：114-121．
CAI Zexiang, WANG Xinghua, REN Xiaona． A review of complex network theory and its application in power systems [J]．Power System Technology, 2012, 36(11): 114-121．
[12] 倪向萍，阮前途，梅生伟，等．基于复杂网络理论的无功分区算法及其在上海电网中的应用[J]．电网技术，2007，31（9）：6-12．
NI Xiangping, RUAN Qiantu, MEI Shengwei, et al． A new network partitioning algorithm based on complex network theory and its application in shanghai power grid [J]． Power System Technology, 2007, 31(9): 6-12．
[13] 罗钢，陈金富，石东源，等．基于复杂网络理论的关键输电断面分析[J]．中国电机工程学报，2013，33（25）：147-155．
LUO Gang, CHEN Jinfu, SHI Dongyuan, et al． Key transmission sections analysis based on complex network theory[J]． Proceedings of the CSEE, 2013, 33(25): 147-155．
[14] 曹一家，陈彦如，曹丽华，等．复杂系统理论在电力系统中的应用研究展望[J]．中国电机工程学报，2012，32（19）：1-9．
CAO Yijia, CHEN Yanru, CAO Lihua, et al． Prospects of studies on application of complex system theory in power systems[J]．Proceedings of CSEE, 2012, 32(19): 1-9．
[15] 高琰，谷士文，唐琎，等．机器学习中谱聚类方法的研究[J]．计算机科学，2007，34（2）：201-203．
GAO Yan, GU Shiwen, TANG Jin, et al． Research on spectral clustering in machine learning [J]． Computer Science, 2007, 34(2): 201-203．
[16] 李生虎，王艳艳，雷庆坤，等．基于改进遗传算法含OLTC风电系统电压控制[J]．中国电力，2015，48（6）：51-58．
LI Shenghu, WANG Yanyan, LEI Qingkun, et al． Voltage control to wind power system with on-load tap changer based on improved genetic algorithm [J]． Electric Power, 2015, 48(6): 51-58．