电力系统高危N-k故障的高危断面辨识与保护配置

doi:10.3969/j.issn.2097-0706.2025.09.001

综合智慧能源 ›› 2025, Vol. 47 ›› Issue (9): 1-9.doi: 10.3969/j.issn.2097-0706.2025.09.001

• 电力系统韧性机理与主动防御 • 下一篇

电力系统高危N-k故障的高危断面辨识与保护配置

黄子书¹(), 蔡晔¹^,^*(), 孙溶佐¹(), 谭玉东²

1.长沙理工大学防灾减灾全国重点实验室，长沙 410114
2.国网湖南省电力有限公司经济技术研究院，长沙 410004

收稿日期:2024-12-05 修回日期:2025-01-15 出版日期:2025-09-25
通讯作者: * 蔡晔（1988），女，副教授，博士，从事电力系统运行与控制、电力市场方面的研究，caiye1988427@126.com
作者简介:黄子书（2001），男，硕士生，从事电力系统安全稳定分析与韧性提升方面的研究，643783077@qq.com；
孙溶佐（1998），男，博士生，从事电力系统安全稳定分析与韧性提升方面的研究，1574259113@qq.com。
基金资助:
国家自然科学基金项目(52277076);湖南省研究生科研创新项目(kq2306011);长沙市杰出创新人才项目(CX20240783)

Critical section identification and protection configuration for high-risk N-k faults in power systems

HUANG Zishu¹(), CAI Ye¹^,^*(), SUN Rongzuo¹(), TAN Yudong²

1. State Key Laboratory of Power Grid Disaster Prevention and Reduction， Changsha University of Science and Technology，Changsha 410114，China
2. State Grid Economic and Technological Research Institute of Hunan，Changsha 410004，China

Received:2024-12-05 Revised:2025-01-15 Published:2025-09-25
Supported by:
National Natural Science Foundation(52277076);Outstanding Innovation Talent Project of Changsha(kq2306011);Hunan Province Graduate Student Research and Innovation Project(CX20240783)

摘要/Abstract

摘要：

针对电力系统N-k连锁故障源发场景多样、故障传播路径复杂、保护策略实施对象难以界定等问题，提出一种结合极限梯度提升（XGBoost）与贝叶斯超参数优化的高危断面辨识与保护配置模型。通过搭建高危N-k故障集，随机模拟0.1~10.0负载率下的连锁故障，构建以线路负载率为输入、剩余负荷为输出目标的连锁故障数据集；使用贝叶斯优化算法调整XGBoost模型超参数，选择最优参数组合；辨识高危N-k故障场景下的保护资源配置策略。在IEEE 39节点系统上的仿真结果表明，对高危N-k故障集中88%的场景，通过调整高危断面3条线路的潮流承载能力，系统剩余负荷可维持在80%以上。

关键词: 连锁故障, 断面辨识, 贝叶斯超参数优化, 数据驱动, XGBoost算法, 机器学习

Abstract:

To address issues such as diverse N-k cascading fault scenarios， complex fault propagation paths， and difficulties in determining protection strategy implementation targets， a critical section identification and protection configuration model that integrates XGBoost with Bayesian hyperparameter optimization is proposed in power systems. By constructing a high-risk N-k fault set and randomly simulating cascading faults under load rates ranging from 0.1~10.0， a cascading fault dataset was developed using line load rates as inputs and residual load as the target. The Bayesian optimization algorithm was used to fine-tune the hyperparameters of the XGBoost model， selecting the optimal parameter combination. The protection resource allocation strategies for high-risk N-k fault scenarios were then identified. Simulation results on the IEEE 39-bus system showed that for 88% of high-risk N-k fault scenarios， adjusting the power flow carrying capacity of three critical section lines enabled the system's residual load to remain above 80%.

Key words: cascading faults, section identification, Bayesian hyperparameter optimization, data-driven, XGBoost algorithm, machine learning

中图分类号:

TK01：TM73

黄子书, 蔡晔, 孙溶佐, 谭玉东. 电力系统高危N-k故障的高危断面辨识与保护配置[J]. 综合智慧能源, 2025, 47(9): 1-9.

HUANG Zishu, CAI Ye, SUN Rongzuo, TAN Yudong. Critical section identification and protection configuration for high-risk N-k faults in power systems[J]. Integrated Intelligent Energy, 2025, 47(9): 1-9.

图/表 11

图1

表1

表2

图2

图3

表3

表4

图4

图5

表5

表6

IEEE 39节点系统高危N-3故障下的模型性能指标汇总

故障编号	MAE	MSE	RMSE	$R 2$
1	0.008 47	0.000 35	0.018 89	0.992
2	0.007 09	0.000 30	0.017 46	0.993
3	0.007 52	0.0002 2	0.014 90	0.992
4	0.010 55	0.000 47	0.021 84	0.992
5	0.002 50	0.000 27	0.016 47	0.995
6	0.005 68	0.000 33	0.018 20	0.994
7	0.006 27	0.000 20	0.014 25	0.996
8	0.002 60	0.000 13	0.011 79	0.997
9	0.006 98	0.000 16	0.012 93	0.997
10	0.003 39	0.000 10	0.010 11	0.997
11	0.001 75	0.000 11	0.010 85	0.997
12	0.002 23	0.000 18	0.013 48	0.997
13	0.005 92	0.000 19	0.013 89	0.996

表6

参考文献 29

[1]	孙华东, 许涛, 郭强, 等. 英国“8·9” 大停电事故分析及对中国电网的启示[J]. 中国电机工程学报, 2019, 39(21): 6183-6192.
	SUN Huadong, XU Tao, GUO Qiang, et al. Analysis on blackout in Great Britain power grid on August 9th, 2019 and its enlightenment to power grid in China[J]. Proceedings of the CSEE, 2019, 39(21): 6183-6192.
[2]	王国春, 董昱, 许涛, 等. 巴西“8·15” 大停电事故分析及启示[J]. 中国电机工程学报, 2023, 43(24): 9461-9470.
	WANG Guochun, DONG Yu, XU Tao, et al. Analysis and lessons of Brazil blackout event on August 15, 2023[J]. Proceedings of the CSEE, 2023, 43(24): 9461-9470.
[3]	余鹏飞, 熊小伏, 朱继忠, 等. 基于储能参与的电网连锁跳闸主动防控方法[J]. 电力系统自动化, 2024, 48(1): 119-130.
	YU Pengfei, XIONG Xiaofu, ZHU Jizhong, et al. Active prevention and control method against power grid cascading tripping based on participation of energy storage[J]. Automation of Electric Power Systems, 2024, 48(1): 119-130.
[4]	邵瑶, 汤涌, 易俊, 等. 土耳其“3·31” 大停电事故分析及启示[J]. 电力系统自动化, 2016, 40(23): 9-14.
	SHAO Yao, TANG Yong, YI Jun, et al. Analysis and lessons of blackout in Turkey power grid on March 31, 2015[J]. Automation of Electric Power Systems, 2016, 40(23): 9-14.
[5]	路尧, 顾晓希, 尹硕, 等. 考虑断面负载率的县域内部新能源电力自平衡交易调度策略研究[J]. 综合智慧能源, 2022, 44(7): 66-72. doi: 10.3969/j.issn.2097-0706.2022.07.008
	LU Yao, GU Xiaoxi, YIN Shuo, et al. Research on county-level self-balance transaction scheduling strategy for new energy considering section load rate[J]. Integrated Intelligent Energy, 2022, 44(7): 66-72. doi: 10.3969/j.issn.2097-0706.2022.07.008
[6]	周德才, 张保会, 姚峰, 等. 基于图论的输电断面快速搜索[J]. 中国电机工程学报, 2006, 26(12): 32-38.
	ZHOU Decai, ZHANG Baohui, YAO Feng, et al. Fast search for transmission section based on graph theory[J]. Proceedings of the CSEE, 2006, 26(12): 32-38.
[7]	曾凯文, 文劲宇, 程时杰, 等. 复杂电网连锁故障下的关键线路辨识[J]. 中国电机工程学报, 2014, 34(7): 1103-1112.
	ZENG Kaiwen, WEN Jinyu, CHENG Shijie, et al. Critical line identification of complex power system in cascading failure[J]. Proceedings of the CSEE, 2014, 34(7): 1103-1112.
[8]	李勇, 刘俊勇, 刘晓宇, 等. 基于潮流熵的电网连锁故障传播元件的脆弱性评估[J]. 电力系统自动化, 2012, 36(19): 11-16.
	LI Yong, LIU Junyong, LIU Xiaoyu, et al. Vulnerability assessment in power grid cascading failures based on entropy of power flow[J]. Automation of Electric Power Systems, 2012, 36(19): 11-16.
[9]	刘文颖, 蔡万通, 张宁, 等. 基于联合加权熵的电网自组织临界状态演化[J]. 中国电机工程学报, 2015, 35(6): 1363-1370.
	LIU Wenying, CAI Wantong, ZHANG Ning, et al. Evolution of self-organizing of grid critical state based on united weighted entropy theory[J]. Proceedings of the CSEE, 2015, 35(6): 1363-1370.
[10]	曹一家, 陈晓刚, 孙可. 基于复杂网络理论的大型电力系统脆弱线路辨识[J]. 电力自动化设备, 2006, 26(12): 1-5, 31.
	CAO Yijia, CHEN Xiaogang, SUN Ke. Identification of vulnerable lines in power grid based on complex network theory[J]. Electric Power Automation Equipment, 2006, 26(12): 1-5, 31.
[11]	张殷, 肖先勇, 李长松. 考虑信息物理交互的电力-信息耦合网络脆弱性分析与改善策略研究[J]. 电网技术, 2018, 42(10): 3136-3147.
	ZHANG Yin, XIAO Xianyong, LI Changsong. Vulnerability analysis and improvement strategy of power-information coupled networks considering cyber physical interaction[J]. Power System Technology, 2018, 42(10): 3136-3147.
[12]	徐岩, 雷小双, 秦彬, 等. 基于综合重要度的电网关键线路辨识方法[J]. 电力建设, 2019, 40(7): 85-90. doi: 10.3969/j.issn.1000-7229.2019.07.011
	XU Yan, LEI Xiaoshuang, QIN Bin, et al. Method based on comprehensive importance for critical line identification in a power grid[J]. Electric Power Construction, 2019, 40(7): 85-90. doi: 10.3969/j.issn.1000-7229.2019.07.011
[13]	陈洋, 翁伟杰, 黄江东, 等. 一种基于变压器的多路径均衡拓扑结构研究[J]. 综合智慧能源, 2024, 46(4): 68-77. doi: 10.3969/j.issn.2097-0706.2024.04.009
	CHEN Yang, WENG Weijie, HUANG Jiangdong, et al. Research on multi-path balancing topology based on transformers[J]. Integrated Intelligent Energy, 2024, 46(4): 68-77. doi: 10.3969/j.issn.2097-0706.2024.04.009
[14]	冀星沛, 王波, 刘涤尘, 等. 相依网络理论及其在电力信息-物理系统结构脆弱性分析中的应用综述[J]. 中国电机工程学报, 2016, 36(17): 4521-4533.
	JI Xingpei, WANG Bo, LIU Dichen, et al. Review on interdependent networks theory and its applications in the structural vulnerability analysis of electrical cyber-physical system[J]. Proceedings of the CSEE, 2016, 36(17): 4521-4533.
[15]	林攀, 吴佳毅, 黄涛, 等. 电力系统脆弱性评估综述[J]. 智慧电力, 2021, 49(1): 22-28.
	LIN Pan, WU Jiayi, HUANG Tao, et al. Overview of vulnerability assessment for power systems[J]. Smart Power, 2021, 49(1): 22-28.
[16]	刘威, 张东霞, 王新迎, 等. 基于深度强化学习的电网紧急控制策略研究[J]. 中国电机工程学报, 2018, 38(1): 109-119, 347.
	LIU Wei, ZHANG Dongxia, WANG Xinying, et al. A decision making strategy for generating unit tripping under emergency circumstances based on deep reinforcement learning[J]. Proceedings of the CSEE, 2018, 38(1): 109-119, 347.
[17]	汪康康, 梅生伟, 魏巍, 等. 基于图卷积网络的快速暂态安全评估方法[J]. 电力系统保护与控制, 2023, 51(1): 43-51.
	WANG Kangkang, MEI Shengwei, WEI Wei, et al. Fast transient security assessment based on graph neural networks[J]. Power System Protection and Control, 2023, 51(1): 43-51.
[18]	韩泽雷, 鞠平, 秦川, 等. 面向新型电力系统的频率安全研究综述与展望[J]. 电力自动化设备, 2023, 43(9): 112-124.
	HAN Zelei, JU Ping, QIN Chuan, et al. Review and prospect of research on frequency security of new power system[J]. Electric Power Automation Equipment, 2023, 43(9): 112-124.
[19]	卫志农, 裴蕾, 陈胜, 等. 高比例新能源交直流混合配电网优化运行与安全分析研究综述[J]. 电力自动化设备, 2021, 41(9): 85-94.
	WEI Zhinong, PEI Lei, CHEN Sheng, et al. Review on optimal operation and safety analysis of AC/DC hybrid distribution network with high proportion of renewable energy[J]. Electric Power Automation Equipment, 2021, 41(9): 85-94.
[20]	孙宏斌, 王康, 张伯明, 等. 采用线性决策树的暂态稳定规则提取[J]. 中国电机工程学报, 2011, 31(34): 61-67, 8.
	SUN Hongbin, WANG Kang, ZHANG Boming, et al. Rule extraction in transient stability study using linear decision trees[J]. Proceedings of the CSEE, 2011, 31(34): 61-67, 8.
[21]	赵津蔓, 韩肖清, 牛哲文, 等. 考虑暂态稳定过程的电力系统运行状态辨识[J]. 中国电机工程学报, 2024, 44(20): 7970-7982.
	ZHAO Jinman, HAN Xiaoqing, NIU Zhewen, et al. Power system operation state identification considering the process of transient stability[J]. Proceedings of the CSEE, 2024, 44(20): 7970-7982.
[22]	朱继忠, 黄林莹, 陈一熙. 基于代理梯度深度强化学习的电力系统网络攻击事后安全控制策略[J]. 电网技术, 2024, 48(10): 4041-4052.
	ZHU Jizhong, HUANG Linying, CHEN Yixi. Surrogate gradient-based deep reinforcement learning for power system post-contingency safety control against cyber-attacks[J]. Power System Technology, 2024, 48(10): 4041-4052.
[23]	张晨宇, 王慧芳, 叶晓君. 基于XGBoost算法的电力系统暂态稳定评估[J]. 电力自动化设备, 2019, 39(3): 77-83, 89.
	ZHANG Chenyu, WANG Huifang, YE Xiaojun. Transient stability assessment of power system based on XGBoost algorithm[J]. Electric Power Automation Equipment, 2019, 39(3): 77-83, 89.
[24]	于琳琳, 王泽, 郝元钊, 等. 基于XGBoost的电力系统动态频率响应曲线预测方法[J]. 电力建设, 2023, 44(4): 74-81. doi: 10.12204/j.issn.1000-7229.2023.04.009
	YU Linlin, WANG Ze, HAO Yuanzhao, et al. XGBoost-based power system dynamic frequency-response curve prediction[J]. Electric Power Construction, 2023, 44(4): 74-81. doi: 10.12204/j.issn.1000-7229.2023.04.009
[25]	HE F F, ZHOU J Z, FENG Z K, et al. A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm[J]. Applied Energy, 2019, 237: 103-116.
[26]	蔡晔, 孙溶佐, 王炜宇, 等. 计及连锁故障传播路径的电力系统N-k多阶段双层优化及故障场景筛选模型[J]. 中国电机工程学报,1-14(2024-01-25)[2024-09-23].https://doi.org/10.13334/j.0258-8013.pcsee.232298.
	CAI Ye, SUN Rongzuo, WANG Weiyu, et al. N-k multi-stage bi-level optimization and fault scenario screening model of power system considering cascading failure propagation path[J]. Proceedings of the CSEE,1-14(2024-01-25)[2024-09-23].https://doi.org/10.13334/j.0258-8013.pcsee.232298.
[27]	刘文霞, 张书宁, 张艺伟, 等. 计及系统运行状态转换的含风电电力通信耦合网络连锁故障建模[J/OL]. 中国电机工程学报,1-13(2023-08-31)[2024-09-23].https://doi.org/10.13334/j.0258-8013.pcsee.231209.
	LIU Wenxia, ZHANG Shuning, ZHANG Yiwei, et al. Cascading failure modeling of power communication coupled network with wind power considering system operating state transition[J/OL]. Proceedings of the CSEE,1-13(2023-08-31)[2024-09-23].https://doi.org/10.13334/j.0258-8013.pcsee.231209.
[28]	CAI Y, CAO Y J, LI Y, et al. Cascading failure analysis considering interaction between power grids and communication networks[J]. IEEE Transactions on Smart Grid, 2016, 7(1): 530-538.
[29]	CHEN T Q, GUESTRIN C. XGBoost: A scalable tree boosting system[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 785-794.

方案	^#6 线路配置参数	^#7 线路配置参数	^#16 线路配置参数	^#17 线路配置参数	^#21 线路配置参数	^#24 线路配置参数	^#31 线路配置参数	剩余负荷率
1	0.957 039 598	0	0	0.763 423 436	0	0	0.246 646 047	0.122
2	0	0	0.416 252 147	0	0	0	0	0.203
3	0	0.523 962 388	0.951 261 251	0.943 495 071	0.869 435 651	0.321 950 269	0.481 167 578	1.000

方案	^#6 线路配置参数	^#7 线路配置参数	^#12 线路配置参数	^#15 线路配置参数	^#16 线路配置参数	^#17 线路配置参数	^#24 线路配置参数	剩余负荷率
1	0.854 405 488	0.156 178 821	0.508 089 055	0.142 051 600	0.186 611 352	0.505 783 843	0	0.805
2	0.738 698 860	0.423 310 533	0	0	0.145 289 630	0	0.735 620 270	0.345
3	0.672 234 557	0.531 174 209	0	0.996 951 188	0.372 555 411	0.864 570 002	0.604 754 507	0.294

故障编号	配置1条线路	配置2条线路	配置3条线路	配置4条线路	配置5条线路	配置6条线路	未配置时
1	0.547	0.805	0.805	0.999	1.000	1.000	0.202
2	0.828	0.828	0.928	0.954	1.000		0.484
3	0.853	0.853	0.954	0.999	0.999	1.000	0.381
4	0.805	0.807	0.999	1.000	1.000	1.000	0.603
5	0.804	0.807	0.807	0.807	0.807	0.808	0.603
6	0.619	0.795	0.919	0.999	0.999	1.000	0.248
7	0.835	0.855	1.000	1.000	1.000	1.000	0.484
8	0.425	0.450	0.705	0.850	0.999	1.000	0.279
9	0.484	0.855	0.855	0.955	1.000	1.000	0.102
10	0.999	1.000	1.000				0.918
11	0.919	0.955	0.966	1.000	1.000	1.000	0.618
12	0.651	0.966	0.999	0.999	0.999	0.999	0.384
13	0.650	0.954	0.954	0.999	0.999	1.000	0.473

故障编号	配置1条线路	配置2条路	配置3条线路	配置4条路	配置5条线路	配置6条线路	未配置时
1	0.603	0.603	0.805	0.805	0.999	0.999	0.603
2	0.345	0.484	0.829	0.829	0.930	0.955	0.345
3	0.473	0.558	0.558	0.619	0.954	0.954	0.370
4	0.370	0.795	0.834	0.919	0.920	0.999	0.370
5	0.796	0.796	0.835	0.919	0.919	1.000	0.370
6	0.491	0.537	0.805	0.805	0.973	0.973	0.232
7	0.491	0.722	0.805	0.805	0.999	0.999	0.118
8	0.547	0.702	0.805	0.895	0.999	1.000	0.202
9	0.547	0.805	0.805	0.807	0.999	0.999	0.202
10	0.491	0.685	0.722	0.805	0.805	0.999	0.232
11	0.547	0.635	0.805	0.828	0.999	1.000	0.202
12	0.549	0.807	0.808	1.000	1.000	1.000	0.203
13	0.547	0.805	0.807	0.999	0.999	1.000	0.202

故障编号	MAE	MSE	RMSE	R²
1	0.006 13	0.000 210	0.014 57	0.996
2	0.007 25	0.000 330	0.018 21	0.993
3	0.003 40	0.000 140	0.012 19	0.996
4	0.004 39	0.000 250	0.015 97	0.995
5	0.002 17	0.000 210	0.014 55	0.995
6	0.002 51	0.000 200	0.014 27	0.996
7	0.001 97	0.000 240	0.015 70	0.995
8	0.002 66	0.000 140	0.012 18	0.995
9	0.001 27	0.000 160	0.012 91	0.996
10	0.000 11	0.000 004	0.002 00	0.997
11	0.003 12	0.000 570	0.023 99	0.989
12	0.005 19	0.000 290	0.017 07	0.994
13	0.008 94	0.000 360	0.019 17	0.993

电力系统高危N-k故障的高危断面辨识与保护配置

Critical section identification and protection configuration for high-risk N-k faults in power systems

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 29

相关文章 15

编辑推荐

Metrics

本文评价

[1]	黄问铉, 曾浩政, 林奕津, 殷林飞. 基于数据驱动方法的磁性元件损耗研究[J]. 综合智慧能源, 2025, 47(4): 73-84.
[2]	张冬冬, 李芳凝, 刘天皓. 新型电力系统负荷预测关键技术及多元场景应用[J]. 综合智慧能源, 2025, 47(3): 47-61.
[3]	邸亮, 董杰, 闫馨月, 甄成, 田喆, 牛纪德. 用于市场准入条件判定的建筑需求响应潜力量化方法[J]. 综合智慧能源, 2025, 47(3): 15-22.
[4]	石鑫, 刘奇央, 高峰. 深度神经网络在新型能源系统中的应用及展望[J]. 综合智慧能源, 2025, 47(2): 88-101.
[5]	邓振宇, 汪茹康, 徐钢, 云昆, 王颖. 综合能源系统中热电联产机组故障预警现状[J]. 综合智慧能源, 2024, 46(8): 67-76.
[6]	王亮, 邓松. 面向新型电力系统的异常数据检测方法[J]. 综合智慧能源, 2024, 46(5): 12-19.
[7]	朱卫卫, 朱清, 高文森, 刘财华, 王录泽, 刘增稷. 基于5G通信时延的配电网馈线自动化切换方法[J]. 综合智慧能源, 2024, 46(5): 1-11.
[8]	陈勇, 肖雷鸣, 王井南, 吴健. 基于场景扩充的低碳综合能源系统高可靠性容量规划方法[J]. 综合智慧能源, 2024, 46(4): 24-33.
[9]	任一鸣, 杜董生, 邓祥帅, 连贺, 赵哲敏. 基于GRU和GWO-KELM的电力线路故障诊断[J]. 综合智慧能源, 2024, 46(3): 54-62.
[10]	李彩霞, 赵军, 李建伟, 王伟, 王杰, 于浩洋. 基于数据驱动的CFB机组变负荷工况SO₂质量浓度建模[J]. 综合智慧能源, 2022, 44(3): 63-69.
[11]	侯鲁洋, 葛磊蛟, 王飚, 王宣元, 徐连明, 王莉. 面向新型产消者的综合能源系统和电力市场研究[J]. 综合智慧能源, 2022, 44(12): 40-48.
[12]	石立宝, 翟放. 考虑风-光-荷不确定性的数据驱动型机组组合模型[J]. 综合智慧能源, 2022, 44(1): 18-25.
[13]	韩旭东. 基于数据驱动的火电机组高压加热系统异常检测研究[J]. 华电技术, 2021, 43(8): 67-73.
[14]	施杰, 张安勤. 基于多参数代价敏感系数学习及数据驱动模型的电力能耗预测[J]. 华电技术, 2021, 43(8): 54-60.
[15]	贾志军, 白德龙, 宋燕杰, 王剑飞, 李春新. 基于KPCA算法的电厂设备在线故障诊断研究[J]. 华电技术, 2021, 43(8): 48-53.