基于多尺度特征集的高占比新能源电网连锁故障数据驱动辨识方法

doi:10.12204/j.issn.1000-7229.2023.06.010

电力建设 ›› 2023, Vol. 44 ›› Issue (6): 91-100.doi: 10.12204/j.issn.1000-7229.2023.06.010

基于多尺度特征集的高占比新能源电网连锁故障数据驱动辨识方法

李国庆¹(), 张斌¹(), 肖桂莲¹(), 刘大贵¹(), 范慧静²(), 甄钊²(), 任惠²()

1.国网新疆电力有限公司,乌鲁木齐市 830000
2.华北电力大学(保定)电力工程系,河北省保定市 071003

收稿日期:2022-07-22 出版日期:2023-06-01 发布日期:2023-05-25
作者简介:李国庆(1981),男,硕士,高级工程师,主要从事电网调度运行、水电及新能源研究工作,E-mail:448776957@qq.com;
张斌(1989),女,硕士,工程师,主要从事新能源运行分析工作,E-mail:1493204726@qq.com;
肖桂莲(1974),女,高级工程师,主要从事新能源调度运行管理工作,E-mail:xjsdxny@sina.com.cn;
刘大贵(1984),男,博士,高级工程师,主要从事新能源运行分析工作,E-mail:deardagui126@126.com;
范慧静(1998),女,硕士研究生,主要研究方向为新能源功率预测技术,E-mail:huijingfan@ncepu.edu.cn;
甄钊(1989),男,博士,主要研究方向为新能源功率预测技术,E-mail:zhenzhao@ncepu.edu.cn;
任惠(1981),女,博士,教授,博士生导师,主要研究方向为电力系统连锁故障风险及早期预警、复杂系统方法在电力系统中的应用,E-mail:hren@ncepu.edu.cn。
基金资助:
国家自然科学基金青年科学基金项目(52007092);国家自然科学基金青年科学基金项目(51107040);国网新疆电力公司科技项目(SGXJ0000TKJS2100234)

Data-Driven Cascading Failure Prediction Method for High-Proportion Renewable Energy Systems Based on Multi-scale Topological Features

LI Guoqing¹(), ZHANG Bin¹(), XIAO Guilian¹(), LIU Dagui¹(), FAN Huijing²(), ZHEN Zhao²(), REN Hui²()

1. State Grid Xinjiang Electric Power Co., Ltd., Urumqi 830000, China
2. Department of Electrical Engineering, North China Electric Power University, Baoding 071003, Hebei Province, China

Received:2022-07-22 Online:2023-06-01 Published:2023-05-25
Supported by:
National Natural Science Foundation of China(52007092);National Natural Science Foundation of China(51107040);Science and Technology Project of State Grid Xinjiang Electric Power Company(SGXJ0000TKJS2100234)

摘要/Abstract

摘要：

随着我国新型电力系统建设进程的不断推进,电力系统运行工况的不确定性大大增加,抗扰动能力更低,连锁故障发生率更高,演化时间更短。传统的基于潮流计算的方法依赖对场景的枚举考虑随机因素,时效性和准确率都难以应对高占比新能源电网复杂的运行工况,因此,提出一种挖掘历史数据规律的基于多尺度特征集的高占比新能源电网连锁故障数据驱动辨识方法,充分考虑历史运行数据中包含的随机信息。从宏观、中观、微观3个层次提取能够表征复杂网络拓扑特征与系统运行状态的特征指标,构成特征指标集;基于双向长短期记忆神经网络学习历史连锁故障过程中复杂网络特征指标与系统运行状态间的映射关系,构建高占比新能源电网连锁故障辨识模型,并通过新疆电网拓扑验证了所提模型的有效性。

关键词: 连锁故障, 数据驱动, 拓扑特征, 高占比新能源, 复杂网络

Abstract:

With the continuous advancement in the renewable power system construction process, the uncertainty of system operating conditions has significantly increased, resulting in a lower antidisturbance ability, higher cascading failure occurrence rate, and shorter evolution time. The traditional power-flow calculation method relies on the enumeration of scenarios to consider random factors, making it difficult to cope with the complex operating conditions experienced with a high percentage of new energy grids in terms of timeliness and accuracy. Therefore, a multi-scale feature-set-based data-driven method for identifying cascading faults under conditions of having a high percentage of new energy grids is proposed by mining historical data patterns and fully considering the stochastic information contained in historical operation data. Indexes that can describe the topological characteristics of a complex network and the operation state of the system are extracted from the macro-, meso-, and micro-levels to form the index set. Based on a bidirectional long-term and short-term memory neural network, the mapping relationship between the index set and the system operation state is studied using the historical cascading failure dataset. This enables a cascading fault prediction model of a high-proportion renewable power system to be constructed. The effectiveness of the proposed model is verified using the topology of the Xinjiang power-grid system.

Key words: cascading failure, data-driven, topological features, high-proportion renewable energy, complex network

中图分类号:

TM732

李国庆, 张斌, 肖桂莲, 刘大贵, 范慧静, 甄钊, 任惠. 基于多尺度特征集的高占比新能源电网连锁故障数据驱动辨识方法[J]. 电力建设, 2023, 44(6): 91-100.

LI Guoqing, ZHANG Bin, XIAO Guilian, LIU Dagui, FAN Huijing, ZHEN Zhao, REN Hui. Data-Driven Cascading Failure Prediction Method for High-Proportion Renewable Energy Systems Based on Multi-scale Topological Features[J]. ELECTRIC POWER CONSTRUCTION, 2023, 44(6): 91-100.

图/表 12

图1 所提方法总体框架

Fig.1 Overall framework of the proposed method

图2 LSTM单元结构

Fig.2 Structure of LSTM unit

图3 Bi-LSTM结构

Fig.3 Structure of Bi-LSTM

图4 新疆电网仿真节点拓扑结构

Fig.4 Node topology of Xinjiang power grid

表1 新疆电网仿真模型各地市对应节点

Table 1 Relationship between cities and nodes in Xinjiang power grid simulation model

表2 支路开断状态第二、三级故障辨识结果精度

Table 2 Forecasting results accuracy of n=2 and n=3 cascading failure

图5 支路开断状态第二、三级故障辨识结果

Fig.5 Forecasting results of n=2 and n=3 cascading failure

表3 典型支路各级故障次数及预测精度

Table 3 Typical branches failure numbers and forecasting accuracy

图6 各支路100次预测稳定性统计结果

Fig.6 Statistics for stability of 100 forecasts

表4 提出模型单条支路训练及预测时间

Table 4 Propose model single branch training and forecasting time

图7 不同人工智能模型预测结果

Fig.7 Different artificial intelligence model forecasting results

图8 不同指标集输入模型预测结果

Fig.8 Different indicators input model forecasting results

参考文献 31

[1]	胡福年, 陈灵娟, 陈军. 基于交流潮流的连锁故障建模与鲁棒性评估[J]. 电力系统保护与控制, 2021, 49(18): 35-43.
	HU Funian, CHEN Lingjuan, CHEN Jun. Cascading failure modeling and robustness evaluation based on AC power flow[J]. Power System Protection and Control, 2021, 49(18): 35-43.
[2]	李妍莎, 蔡晔, 曹一家, 等. 面向联合检修的电力信息物理系统输电线路脆弱相关性辨识[J]. 电力系统保护与控制, 2022, 50(24): 120-128.
	LI Yansha, CAI Ye, CAO Yijia, et al. Vulnerable correlation identification of a transmission line in the power cyber physical system for federated maintenance[J]. Power System Protection and Control, 2022, 50(24): 120-128.
[3]	易俊, 卜广全, 郭强, 等. 巴西“3·21”大停电事故分析及对中国电网的启示[J]. 电力系统自动化, 2019, 43(2): 1-6.
	YI Jun, BU Guangquan, GUO Qiang, et al. Analysis on blackout in Brazilian power grid on March 21, 2018 and its enlightenment to power grid in China[J]. Automation of Electric Power Systems, 2019, 43(2): 1-6.
[4]	曾辉, 孙峰, 李铁, 等. 澳大利亚“9·28”大停电事故分析及对中国启示[J]. 电力系统自动化, 2017, 41(13): 1-6.
	ZENG Hui, SUN Feng, LI Tie, et al. Analysis of “9·28” blackout in south Australia and its enlightenment to China[J]. Automation of Electric Power Systems, 2017, 41(13): 1-6.
[5]	REZAEI P, HINES P D H, EPPSTEIN M J. Estimating cascading failure risk with random chemistry[J]. IEEE Transactions on Power Systems, 2015, 30(5): 2726-2735. doi: 10.1109/TPWRS.2014.2361735 URL
[6]	马志远, 石立宝, 姚良忠, 等. 电网连锁故障的事故链搜索模型及策略研究[J]. 中国电机工程学报, 2015, 35(13): 3292-3302.
	MA Zhiyuan, SHI Libao, YAO Liangzhong, et al. Study on the modeling and search strategy of event chain for cascading failure in power grid[J]. Proceedings of the CSEE, 2015, 35(13): 3292-3302.
[7]	丁明, 肖遥, 张晶晶, 等. 基于事故链及动态故障树的电网连锁故障风险评估模型[J]. 中国电机工程学报, 2015, 35(4): 821-829.
	DING Ming, XIAO Yao, ZHANG Jingjing, et al. Risk assessment model of power grid cascading failures based on fault chain and dynamic fault tree[J]. Proceedings of the CSEE, 2015, 35(4): 821-829.
[8]	刘文颖, 但扬清, 朱艳伟, 等. 复杂电网自组织临界态辨识物理指标研究[J]. 电工技术学报, 2014, 29(8): 274-280, 288.
	LIU Wenying, DAN Yangqing, ZHU Yanwei, et al. Research on physical indicators to identify power system self-organized critical state[J]. Transactions of China Electrotechnical Society, 2014, 29(8): 274-280, 288.
[9]	胡萍, 梅挺, 范文礼. 复杂电网连锁故障预测研究综述[J]. 中国科学: 技术科学, 2017, 47(4): 355-363.
	HU Ping, MEI Ting, FAN Wenli. Cascading failure forecast of complex power grids: a review[J]. Scientia Sinica (Technologica), 2017, 47(4): 355-363.
[10]	刘文霞, 黄钰辰, 万海洋, 等. 复杂网络理论在能源互联网脆弱性与鲁棒性研究中的应用[J]. 智慧电力, 2021, 49(1): 14-21.
	LIU Wenxia, HUANG Yuchen, WAN Haiyang, et al. Application of complex network theory in vulnerability and robustness evaluation of energy Internet[J]. Smart Power, 2021, 49(1): 14-21.
[11]	王宇飞, 李俊娥, 邱健, 等. 计及攻击损益的跨空间连锁故障选择排序方法[J]. 电网技术, 2018, 42(12): 3926-3937.
	WANG Yufei, LI June, QIU Jian, et al. A novel selection sorting method of cascading failures across space considering attack gain and cost[J]. Power System Technology, 2018, 42(12): 3926-3937.
[12]	吕歆瑶, 李华强, 郑国, 等. 基于综合脆性关联度的连锁故障预测与冲击辨识[J]. 电力自动化设备, 2015, 35(12): 116-121, 125.
	LÜ Xinyao, LI Huaqiang, ZHENG Guo, et al. Cascading failure forecast and impact identification based on comprehensive brittleness relevance[J]. Electric Power Automation Equipment, 2015, 35(12): 116-121, 125.
[13]	鲁宗相, 黄瀚, 单葆国, 等. 高比例可再生能源电力系统结构形态演化及电力预测展望[J]. 电力系统自动化, 2017, 41(9): 12-18.
	LU Zongxiang, HUANG Han, SHAN Baoguo, et al. Morphological evolution model and power forecasting prospect of future electric power systems with high proportion of renewable energy[J]. Automation of Electric Power Systems, 2017, 41(9): 12-18.
[14]	鲁宗相, 李昊, 乔颖. 从灵活性平衡视角的高比例可再生能源电力系统形态演化分析[J]. 全球能源互联网, 2021, 4(1): 12-18.
	LU Zongxiang, LI Hao, QIAO Ying. Morphological evolution analysis of high proportion renewable energy power system from the perspective of flexibility balance[J]. Journal of Global Energy Interconnection, 2021, 4(1): 12-18.
[15]	毛安家, 马静, 蒯圣宇, 等. 高比例新能源替代常规电源后系统暂态稳定与电压稳定的演化机理[J]. 中国电机工程学报, 2020, 40(9): 2745-2756.
	MAO Anjia, MA Jing, KUAI Shengyu, et al. Evolution mechanism of transient and voltage stability for power system with high renewable penetration level[J]. Proceedings of the CSEE, 2020, 40(9): 2745-2756.
[16]	焦瑞浩, 王震宇, 王克非, 等. 计及大规模风电并网的交直流电网连锁故障熵特征研究[J]. 电测与仪表, 2021, 58(7): 49-56.
	JIAO Ruihao, WANG Zhenyu, WANG Kefei, et al. Study on the entropy characteristics of cascading failure of AC/DC power grid considering large-scale wind power grid-connection[J]. Electrical Measurement & Instrumentation, 2021, 58(7): 49-56.
[17]	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.
[18]	沈政委, 孙华东, 汤涌, 等. 传统交流电网与高比例新能源电网连锁故障差异性分析[J]. 电网技术, 2021, 45(12): 4641-4649.
	SHEN Zhengwei, SUN Huadong, TANG Yong, et al. Analysis of cascading failure differences between traditional AC power grid and high-proportion new energy power grid[J]. Power System Technology, 2021, 45(12): 4641-4649.
[19]	崔晓丹, 吴家龙, 雷鸣, 等. 新能源高占比电力系统的连锁故障诱因及事故链搜索技术探讨[J]. 电力自动化设备, 2021, 41(7): 135-143.
	CUI Xiaodan, WU Jialong, LEI Ming, et al. Discussion on inducement and fault chain search technology of cascading failure in power system with high penetration of renewable energy[J]. Electric Power Automation Equipment, 2021, 41(7): 135-143.
[20]	陈群杰. 基于网络模体的电网连锁故障预警研究[D]. 北京: 华北电力大学, 2017.
	CHEN Qunjie. Research on early warning of power grid cascading failure based on network model[D]. Beijing: North China Electric Power University, 2017.
[21]	任惠, 王根旺, 唐焕新, 等. 基于数据驱动的输电网节点停电风险评估指标研究[J]. 电力系统及其自动化学报, 2021, 33(6): 51-59.
	REN Hui, WANG Genwang, TANG Huanxin, et al. Study on nodal outage risk evaluation index for transmission network based on data-driven method[J]. Proceedings of the CSU-EPSA, 2021, 33(6): 51-59.
[22]	刘杰荣, 张耀宇, 关家华, 等. 基于量测大数据和数学形态学的配电网故障检测及定位方法研究[J]. 智慧电力, 2020, 48(1): 97-104.
	LIU Jierong, ZHANG Yaoyu, GUAN Jiahua, et al. Research on fault detection and location method of distribution network based on measurement big data and mathematical morphology[J]. Smart Power, 2020, 48(1): 97-104.
[23]	KOC Y, WARNIER M, VAN MIEGHEM P, et al. A topological investigation of phase transitions of cascading failures in power grids[J]. Physica A: Statistical Mechanics and its Applications, 2014, 415: 273-284. doi: 10.1016/j.physa.2014.07.083 URL
[24]	BAO Z J, CAO Y J, WANG G Z, et al. Analysis of cascading failure in electric grid based on power flow entropy[J]. Physics Letters A, 2009, 373(34): 3032-3040. doi: 10.1016/j.physleta.2009.06.058 URL
[25]	楼洋, 李均利, 李升, 等. 复杂网络能控性鲁棒性研究进展[J]. 自动化学报, 2022, 48(10): 2374-2391.
	LOU Yang, LI Junli, LI Sheng, et al. Recent progress in controllability robustness of complex networks[J]. Acta Automatica Sinica, 2022, 48(10): 2374-2391.
[26]	顾雪平, 刘雨濛, 王涛, 等. 基于结构平衡理论的电网自组织临界态辨识[J]. 电工技术学报, 2018, 33(17): 4136-4145.
	GU Xueping, LIU Yumeng, WANG Tao, et al. Self-organized critical state identification of power systems based on structural equilibrium theory[J]. Transactions of China Electrotechnical Society, 2018, 33(17): 4136-4145.
[27]	吴煜寰. 基于网络连通度的输电网节点供电能力评估[D]. 北京: 华北电力大学, 2019.
	WU Yuhuan. Evaluation of power supply capacity of transmission network nodes based on network connectivity[D]. Beijing: North China Electric Power University, 2019.
[28]	赵晋斌, 张建平, 毛玲, 等. 基于PSO-Soft attention双向LSTM算法的光伏发电量预测研究[J]. 智慧电力, 2022, 50(3): 1-7.
	ZHAO Jinbin, ZHANG Jianping, MAO Ling, et al. Photovoltaic power generation forecasting based on PSO-soft attention bidirectional LSTM algorithm[J]. Smart Power, 2022, 50(3): 1-7.
[29]	朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802.
	ZHU Qiaomu, LI Hongyi, WANG Ziqi, et al. Short-term wind power forecasting based on LSTM[J]. Power System Technology, 2017, 41(12): 3797-3802.
[30]	谢亮. 基于内点理论最优潮流的算法及应用研究[D]. 上海: 上海交通大学, 2011.
	XIE Liang. Research on algorithm and application of optimal power flow based on interior point theory[D]. Shanghai: Shanghai Jiao Tong University, 2011.
[31]	杨燕. 基于深度神经网络的电力系统潮流分析快速算法及其应用研究[D]. 重庆: 重庆大学, 2021.
	YANG Yan. Research on fast algorithm for power flow analysis of power system based on deep neural network and its application[D]. Chongqing: Chongqing University, 2021.

基于多尺度特征集的高占比新能源电网连锁故障数据驱动辨识方法

Data-Driven Cascading Failure Prediction Method for High-Proportion Renewable Energy Systems Based on Multi-scale Topological Features

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价

[1]	黄梦旗, 李勇汇, 曾海燕, 陈艳, 王宣, 王东旭, 杨军. 计及高渗透率分布式电源的韧性配电网数据驱动鲁棒规划方法[J]. 电力建设, 2023, 44(6): 79-90.
[2]	段忠峰, 王亚松, 白茂金, 刘威, 朱春萍, 王成福, 董晓明. 面向互联电网连锁故障安全防控的关键支路辨识[J]. 电力建设, 2023, 44(1): 12-20.
[3]	滕家琛, 刘洋, 邬嘉雨, 王磊, 张杰. 基于mRMR-XGboost-IDM模型的两阶段可调鲁棒经济调度[J]. 电力建设, 2022, 43(9): 140-150.
[4]	杨秀, 焦楷丹, 孙改平, 陈小毅, 杜佳玮, 仇志鑫. 考虑负荷多无功用电场景的城市配电网无功优化配置[J]. 电力建设, 2022, 43(8): 42-52.
[5]	邓慧琼, 罗杰, 王晓铭, 刘昊, 李培强, 李晨晨. 考虑安全性和经济性的连锁故障预防控制策略[J]. 电力建设, 2022, 43(5): 100-108.
[6]	徐澄莹, 朱旭, 窦真兰, 杨军, 张春雁. 基于数据驱动鲁棒优化的用户侧综合能源舱低碳规划[J]. 电力建设, 2022, 43(12): 27-36.
[7]	张孟琛, 林丽娟, 孟菁, 牛益国, 王珺, 石磊磊. 数据驱动的配电台区源荷污染源群体谐波排放建模[J]. 电力建设, 2021, 42(8): 46-54.
[8]	王珺, 田恩东, 马建, 窦晓波, 刘之涵. 基于数据驱动的非全实时观测配电网无功优化方法[J]. 电力建设, 2021, 42(2): 68-76.
[9]	陆晓, 徐春雷, 冷钊莹, 吴海伟, 陈中. 基于数据驱动方法的疫情阶段电力用户负荷特性画像模型[J]. 电力建设, 2021, 42(2): 93-106.
[10]	张宇威, 肖金星, 杨军, 徐冰雁, 李蕊, 李勇汇. 基于风光数据驱动不确定集合的配电网与多微网鲁棒经济调度[J]. 电力建设, 2021, 42(10): 40-50.
[11]	陈晓东, 马越, 陈贤邦, 刘洋. 基于数据驱动可调鲁棒的冷-热-电联供综合能源系统日前调度优化[J]. 电力建设, 2021, 42(1): 28-40.
[12]	郇嘉嘉，肖勇，陆文升，刘洪，彭家颖，潘险险，李吉峰. 基于复杂网络理论的区域综合能源系统可靠性评估[J]. 电力建设, 2020, 41(4): 1-9.
[13]	王晞, 徐浩, 王海燕, 陈博, 王长浩, 刘洋. 考虑风电和电动汽车不确定性的综合能源系统日前经济调度[J]. 电力建设, 2020, 41(12): 82-91.
[14]	张宇威, 杨军，吴赋章，詹祥澎，龙雪梅，张俊，徐箭. 基于电网-交通网耦合的充电站故障传播分析框架[J]. 电力建设, 2020, 41(1): 13-22.
[15]	梁修锐，刘道伟，杨红英，李卫星，邵广惠，徐兴伟，王克非，李宗翰，赵高尚. 数据驱动的电力系统静态电压稳定态势评估[J]. 电力建设, 2020, 41(1): 126-132.