基于半监督谱聚类的黑启动分区策略

doi:10.3969/j.issn.1000－7229.2017.04.002

电力建设 ›› 2017, Vol. 38 ›› Issue (4): 9-.doi: 10.3969/j.issn.1000－7229.2017.04.002

基于半监督谱聚类的黑启动分区策略

李力1，傅子昊2，孙磊2，杨银国1，谭嫣1，林振智2，文福拴2,3

1.广东电网有限责任公司电力调度控制中心，广州市 510600；2.浙江大学电气工程学院，杭州市 310027；3. 文莱科技大学电机与电子工程系，文莱斯里巴加湾 BE1410

出版日期:2017-04-01
作者简介:李力（1970），女，学士，高级工程师，主要从事电力系统调度运行、电网运行风险分析与控制方面的运行与科研工作；傅子昊（1991），男，硕士，本文通信作者，主要研究方向为电力系统恢复；孙磊（1989），男，博士研究生，主要研究方向为电力系统恢复；杨银国（1980），男，硕士，教授级高工，主要从事电力系统运行与控制、风险管理方面的运行与科研工作；谭嫣（1987），女，硕士，工程师，主要从事电力系统运行与控制方面的运行与科研工作；林振智（1979），男，副教授，硕士生导师，主要研究方向为电力应急与电力系统恢复；文福拴（1965），男，教授，博士生导师，主要研究方向为电力系统故障诊断与系统恢复、电力经济与电力市场、智能电网与电动汽车。
基金资助:
国家高技术研究发展计划项目（863计划）（2015AA050202）；国家自然科学基金项目（51377005）；浙江省重点科技创新团队项目（2010R50004）；
广东电网有限责任公司科技项目（GDKJQQ20153001）

Black-Start Zoning Strategy Based Semi-Supervised Spectral Clustering Algorithm

YANG Yinguo1,　TAN Yan1, LIN Zhenzhi2, WEN Fushuan2,3

1. Power Dispatch and Control Center of Guangdong Power Grid, Guangzhou 510600, China;
2. School of Electrical Engineering, Zhejiang University, Hangzhou 310027, China;

3. Department of Electrical & Electronic Engineering, Universiti Teknologi Brunei, Bandar Seri Begawan BE1410, Brunei

Online:2017-04-01
Supported by:

摘要/Abstract

摘要： 摘要：采用并行恢复策略可以有效加快电力系统发生大停电事故后的恢复进程，而合理的分区策略是并行恢复的基础。现有分区方法多数存在对算法初值依赖性强、难以获得全局最优解等缺点，而半监督谱聚类具有能够识别任意形状的样本空间并能够收敛于全局最优解，且适用于分区问题的特点。在此背景下，提出了基于半监督谱聚类的黑启动分区策略。首先，给定节点间电气距离的倒数为相关线路的权重，在此基础上建立电力系统无向加权图，进而依据比例割集准则建立黑启动分区策略。该策略由2步构成：第一步建立待恢复机组的分组模型，其以给定时间段内最大化系统发电量和最小化恢复线路总电容为优化目标，从而保证机组的安全快速启动；第二步以得到的机组分组信息为基础，利用半监督谱聚类算法求解黑启动分区模型。为了克服传统k-means算法对初始聚类中心敏感的缺点，在利用半监督谱聚类算法对特征向量进行聚类的最后一步采用了k-means++算法对特征向量进行聚类。最后，以新英格兰10机39节点系统和IEEE 30节点系统为例说明了所发展的模型和方法的基本特征。

关键词: 电力系统恢复, 黑启动分区, 半监督谱聚类, k-means++算法

Abstract: Power system restoration after a blackout can be speeded up by employing a parallel restoration strategy, while a reasonable zoning strategy is the basis of parallel restoration. The performances of most of the existing black-start zoning methods are highly dependent on the specified initial values, and it is hard to attain the global optimal solution by these methods. The semi-supervised spectral clustering algorithm is able to identify any shapes of sample spaces, and to attain the global optimal solution, which can be employed for black-start zoning. Given this background, this paper proposes the black-start zoning strategy based on the semi-supervised spectral clustering algorithm. Firstly, the reciprocal of electrical distance between nodes is used to determine the weight of the line, and then the undirected weighted graph of the power system concerned can be formed. On this basis, a black-start zoning strategy is presented based on the ratio cut set criterion. The proposed strategy consists of two steps. In the first step, a grouping optimization model of generators to be restored is presented for speeding the power system restoration, with both the maximization of the restored generation quantity in the given period and the minimization of the total capacitance of the restored transmission lines included in the objective function of the optimization problem. In the second step, the semi-supervised clustering algorithm is employed to solve the black-start zoning model based on the grouping information attained in the first step. In the the last step of semi-supervised spectral clustering algorithm, the k-means++ algorithm is employed to cluster the feature vectors, so as to avoid the drawback of the traditional k-means algorithm that the clustering result is sensitive to the specified initial cluster centers. Finally, the New England 10-unit 39-bus power system and IEEE 30-bus power system are employed to demonstrate the basic features of the developed model and method.

Key words: power system restoration, black-start zone partitioning, semi-supervised clustering algorithm, k-means++ algorithm

中图分类号:

TM 711

李力，傅子昊，孙磊，杨银国，谭嫣，林振智，文福拴. 基于半监督谱聚类的黑启动分区策略[J]. 电力建设, 2017, 38(4): 9-.

YANG Yinguo,　TAN Yan, LIN Zhenzhi, WEN Fushuan. Black-Start Zoning Strategy Based Semi-Supervised Spectral Clustering Algorithm[J]. Electric Power Construction, 2017, 38(4): 9-.

参考文献

［1］〖HJ1.4mm〗U.S.-Canada Power System Outage Task Force.Final report on the August 14th blackout in the United States and Canada［EB/OL］. （2004-4）［2017-03-09］. https://www.ferc.gov/industries/electric/indus-act/reliability/blackout/ch1-3.pdf.

［2］ANDERSSON G, DONALEK P, FARMER R, et al. Causes of the 2003 major grid blackouts in North America and Europe, and recommended means to improve system dynamic performance ［J］. IEEE Transactions on Power Systems, 2005, 20（4）: 1922-1928.

［3］杨永全. 近年电网冰灾事故分析及抗防对策［J］. 电力建设, 2008, 29（9）: 35-37.

YANG Yongquan. Analysis of recent icing-caused grid accidents and its countermeasures［J］. Electric Power Construction, 2008, 29（9）: 35-37.

［4］薛禹胜. 印度大停电事故原因分析及对中国电网的警示［J］. 电网与清洁能源, 2012, 28（10）: 1-3.

〖JP3〗XUE Yusheng. The reason analysis of Indian blackout and the warning to China Grid［J］. Power System and Clean Energy, 2012, 28（10）: 1-3.

［5］卫鹏, 安海云, 周前, 等. 基于BPA程序的江苏电网黑启动暂态稳定性研究［J］. 电力建设, 2013, 34（8）: 6-10.

WEI Peng, AN Haiyun, ZHOU Qian, et al. Research of transient stability of Jiangsu power grids black-start based on BPA ［J］. Electric Power Construction, 2013, 34（8）: 6-10.

［6］ADIBI M M, CLELLAND P, FINK L, et al. Power system restoration： A task force report ［J］. IEEE Transactions on Power Systems, 1987, 2（2）: 271-277.

［7］李志民, 刘迎春, 李卫星, 等. 电力系统恢复典型案例分析［J］. 电力系统自动化, 2003, 27（2）: 60-64.

LI Zhimin, LIU Yingchun, LI Weixing, et al.Analysis of typical system restoration examples［J］. Automation of Electric Power Systems, 2003, 27（2）: 60-64.

［8］ADIBI M M, FINK L H. Power system restoration planning ［J］. IEEE Transactions on Power Systems, 1994, 9（1）: 22-28.

［9］WANG C, VITTAL V, SUN K. OBDD-based sectionalizing strategies for parallel power system restoration ［J］. IEEE Transactions on Power Systems, 2011, 26（3）: 1426-1433.

［10］顾雪平, 韩忠晖, 梁海平. 电力系统大停电后系统分区恢复的优化算法［J］. 中国电机工程学报, 2009, 29（10）: 41-46.

GU Xueping, HAN Zhonghui, LIANG Haiping. Optimization of parallel restoration through power system partitioning after blackout ［J］. Proceedings of the CSEE, 2009, 29（10）: 41-46.

［11］林振智, 文福拴, 周浩. 基于复杂网络社团结构的恢复子系统划分算法［J］. 电力系统自动化, 2009, 33（12）: 12-16.

LIN Zhenzhi, WEN Fushuan, ZHOU Hao. A new algorithm for restoration subsystem division based on community structure of complex network theory ［J］. Automation of Electric Power Systems, 2009, 33（12）: 12-16.

［12］孙磊, 张璨, 林振智, 等. 大停电后电力系统黑启动分区的两步策略［J］. 电力自动化设备, 2015, 35（9）: 14-21.

SUN Lei, ZHANG Can, LIN Zhenzhi, et al.Two-step strategy for black-start zone partitioning of power system after blackout ［J］. Electric Power Automation Equipment, 2015, 35（9）: 14-21.

［13］QUIROS J, WALL P, DING L, et al. Determination of sectionalising strategies for parallel power system restoration: A spectral clustering-based methodology ［J］. Electric Power Systems Research, 2014, 116（11）: 381-390.

［14］谭玉东，李欣然，蔡晔, 等. 基于电气距离的复杂电网关键节点识别［J］. 中国电机工程学报, 2014, 34（1）: 146-152.

TAN Yudong, LI Xinran, CAI Ye, et al.Critical node identification for complex power grid based on electrical distance ［J］. Proceedings of the CSEE, 2014, 34（1）: 146-152.

［15］张璨，林振智，文福拴，等. 基于后悔思想的网络重构两步策略［J］. 电力系统自动化, 2013, 37（8）: 46-52, 75.

ZHANG Can，LIN Zhenzhi，WEN Fushuan, et al. A two-stage strategy for network reconfiguration based on the concept of regret ［J］. Automation of Electric Power Systems, 2013, 37（8）: 46-52, 75.

［16］CHAN P K,SCHLAG M D F, ZIEN J Y, et al. Spectral K-way ratio-cut partitioning and clustering ［J］. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1994, 13（9）: 749-754.

［17］LUXBURG U V. A tutorial on spectral clustering ［J］. Statistics & Computing, 2007, 17（4）: 395-416.

［18］LUTKEPOHL H. Handbook of matrices ［M］. Chichester: Wiley, 1997.

［19］ARTHUR D, VASSILVITSKII S.k-means++: the advantages of careful seeding ［C］// Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms. PA, USA, 2007: 1027-1035.

［20］SARMADI S A N, DOBAKHSHARI A S, AZIZI S, et al.A sectionalizing method in power system restoration based on WAMS ［J］. IEEE Transactions on Smart Grid, 2011, 2（1）: 190-197.

［21］WAGSTAFF K, CARDIE C, ROGERS S, et al. Constrained K-means clustering with background knowledge ［C］// Proceedings of the 18th International Conference on Machine Learning. Burlington, Canada, 2001: 577-584.

［22］FINK L H, LIOU K L, LIU C C.From generic restoration actions to specific restoration strategies［J］. IEEE Transactions on Power Systems, 1995, 10（2）: 745-752.

[1]	王亮, 盖振宇, 蒋维勇, 史宇欣, 孟庆萌. ±800 kV雁淮特高压直流系统送端孤岛运行闭锁策略[J]. 电力建设, 2020, 41(8): 40-47.
[2]	郑惠萍, 曾鹏, 刘新元, 程雪婷, 薄利明, 杨尉薇, 张一帆, 崔杨. 基于误差前馈预测的多时空尺度风电集群有功功率分层控制策略[J]. 电力建设, 2020, 41(8): 120-128.
[3]	赵海兵，张焕云，葛杨，程浩原，高文浩，艾芊. 细胞-组织认知下的主动配电系统双层多目标控制策略[J]. 电力建设, 2020, 41(5): 81-92.
[4]	李淋，徐青山，王晓晴，凌静，孙海翔. 基于共享储能电站的工业用户日前优化经济调度[J]. 电力建设, 2020, 41(5): 100-107.
[5]	周洪益，钱苇航，柏晶晶，卫志农，孙国强，臧海祥. 能源区块链的典型应用场景分析及项目实践[J]. 电力建设, 2020, 41(2): 11-20.
[6]	张中丹，李锦键，王兴贵，赵玲霞. 基于静态模型的光热储能电站发电量优化策略[J]. 电力建设, 2019, 40(10): 111-117.
[7]	王星华，刘升伟，陈豪君，彭显刚，周亚武. 考虑用户差异性的售电公司需求响应电价模型[J]. 电力建设, 2019, 40(9): 116-123.
[8]	谢敏，韦薇，李建钊，刘明波. 储能电站参与能量-调频市场联合调度模式研究[J]. 电力建设, 2019, 40(2): 20-28.
[9]	江帆，杨洪耕. 基于选择性贝叶斯分类的非侵入式负荷识别方法[J]. 电力建设, 2019, 40(2): 94-.
[10]	刘中原，王维庆，王海云，袁成玉，王亮，李永钦，丁文彬. 基于VSG技术的VSC-HVDC输电系统受端换流器控制策略[J]. 电力建设, 2019, 40(2): 100-.
[11]	林伟芳，易俊，贾俊川，王安斯，余芳芳，方诗卉. 故障后半波长输电线路的稳态过电压控制措施[J]. 电力建设, 2019, 40(2): 109-.
[12]	. 特约主编寄语[J]. 电力建设, 2018, 39(12): 1-.
[13]	冯麒铭，刘继春，杨阳方，谭心怡，尹龙，孙宁杰. 考虑能源重复转换的综合能源系统经济运行[J]. 电力建设, 2018, 39(12): 47-54.
[14]	田艳军, 陈波，王毅，王慧，魏石磊. DC/DC与DC/AC级联变流器阻抗协调控制策略[J]. 电力建设, 2018, 39(7): 64-73.
[15]	戴志辉，苏怀波,刘宁宁，张程. 基于电流相关性的直流线路单极故障保护方案[J]. 电力建设, 2018, 39(7): 74-80.

基于半监督谱聚类的黑启动分区策略

Black-Start Zoning Strategy Based Semi-Supervised Spectral Clustering Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价