Early warning of security situation for cyber-physical systems of urban power grids based on kernel extreme learning machine

doi:10.3969/j.issn.2097-0706.2025.09.003

Abstract

Abstract:

Timely early warning of security situation in cyber-physical systems （CPS） of urban power grids is critical for ensuring safe and stable operation. To address the early-warning challenges for the operational status of CPS under multiple disturbances， a security situation early warning method based on kernel extreme learning machine （KELM） was proposed. A coupling model of the physical and information layers of the power grid was established by integrating cellular automata theory， and the mechanism of cross-space risk propagation was analyzed； An ensemble KELM early warning model was developed， in which multidimensional data were deeply integrated through radial basis function kernel mapping， and prediction accuracy was enhanced by the ensemble structure； An early warning indicator system was established， and indicator weights were dynamically allocated using the entropy weight method to classify early warning levels of security situation. Simulation experiments based on the IEEE 33-bus distribution network demonstrated that， under distributed generation integration scenarios， the proposed method achieved a 12.49% reduction in mean squared error of voltage fluctuation prediction compared to traditional extreme learning machine methods， verifying the efficiency and robustness of the model.

Key words: cyber-physical system of urban power grid, security situation early warning, cross-space risk propagation, cellular automata, kernel extreme learning machine

CLC Number:

TM73：TK01

XU Ao, WANG Ziyue, XU Junjun, ZHOU Xian. Early warning of security situation for cyber-physical systems of urban power grids based on kernel extreme learning machine[J]. Integrated Intelligent Energy, 2025, 47(9): 18-27.

Figures/Tables 14

Fig.1

Fig.2

Table 1

Fig.3

Fig.4

Fig.5

Table 2

Fig.6

Table 3

Table 4

Thresholds of security situation risks early warning for CPS of urban power grid

预警等级	阈值
0 级	$S (t) < 0.2$
Ⅰ级	$0.2 ≤ S (t) < 0.5$
Ⅱ级	$0.5 ≤ S (t) < 0.8$
Ⅲ级	$S (t) ≥ 0.8$

Table 4

Fig.7

Table 5

Fig.8

Fig.9

References 31

[1]	臧天磊, 刘云飞, 王世俊, 等. 计及故障传播效应的配电信息物理系统多时段维修-恢复协同策略[J]. 电力自动化设备, 2024, 44(12): 247-256.
	ZANG Tianlei, LIU Yunfei, WANG Shijun, et al. Multi-period maintenance and restoration collaborative strategy for cyber physical distribution system considering fault propagation effect[J]. Electric Power Automation Equipment, 2024, 44(12): 247-256.
[2]	李卓, 谢耀滨, 吴茜琼, 等. 基于深度学习的电力系统虚假数据注入攻击检测综述[J]. 电力系统保护与控制, 2024, 52(19): 175-187.
	LI Zhuo, XIE Yaobin, WU Qianqiong, et al. Review of deep learning-based false data injection attack detection in power systems[J]. Power System Protection and Control, 2024, 52(19): 175-187.
[3]	刘友波, 曾宇, 张曦, 等. 城市高压配电网负荷转供辅助决策关键技术与系统[J]. 电力自动化设备, 2023, 43(10): 192-199.
	LIU Youbo, ZENG Yu, ZHANG Xi, et al. Key technology and system for auxiliary decision-making of load transfer in urban high voltage distribution network[J]. Electric Power Automation Equipment, 2023, 43(10): 192-199.
[4]	阮前途, 梅生伟, 黄兴德, 等. 低碳城市电网韧性提升挑战与展望[J]. 中国电机工程学报, 2022, 42(8): 2819-2830.
	RUAN Qiantu, MEI Shengwei, HUANG Xingde, et al. Challenges and research prospects of resilience enhancement of low-carbon power grid[J]. Proceedings of the CSEE, 2022, 42(8): 2819-2830.
[5]	章锐, 于继来. 新型城市电网调控体系架构及关键技术[J]. 中国电机工程学报, 2024, 44(S1): 97-113.
	ZHANG Rui, YU Jilai. New urban power grid dispatching and control architecture and key technologies[J]. Proceedings of the CSEE, 2024, 44(S1): 97-113.
[6]	黄植, 刘东, 陈冠宏, 等. 基于事件驱动的配电信息物理连锁故障演化机理[J]. 电力工程技术, 2022, 41(3): 2-13.
	HUANG Zhi, LIU Dong, CHEN Guanhong, et al. The evolution mechanism of the cyber-physical cascading failure of power distribution system based on event-driven[J]. Electric Power Engineering Technology, 2022, 41(3): 2-13.
[7]	张晶晶, 吴佳瑜, 齐先军, 等. 基于网络依存关系的CPPS连锁故障分析及风险评估[J]. 电力系统保护与控制, 2023, 51(5): 164-171.
	ZHANG Jingjing, WU Jiayu, QI Xianjun, et al. Cascading failure analysis and risk assessment of CPPS based on network dependency[J]. Power System Protection and Control, 2023, 51(5): 164-171.
[8]	张宸赓, 许寅, 王玥, 等. 极寒灾害下电力-天然气耦合系统故障连锁传播过程推演方法[J]. 电网技术, 2024, 48(10): 4084-4095.
	ZHANG Chengeng, XU Yin, WANG Yue, et al. Deduction method for the cascading fault propagation process in integrated power and natural gas systems under extreme cold disasters[J]. Power System Technology, 2024, 48(10): 4084-4095.
[9]	LIU D Q, ZHANG Q, LIANG H L, et al. Modeling and analysis of risk propagation and loss causing capacity for key nodes in cyber-physical coupled power network[J]. Complex System Modeling and Simulation, 2024, 4(2): 124-136.
[10]	赵云龙, 傅文进, 李沛. 基于大数据的配电网运行风险智能预警方法[J]. 自动化应用, 2022(1): 116-118, 122.
	ZHAO Yunlong, FU Wenjin, LI Pei. Intelligent early warning method of distribution network operation risk based on big data[J]. Automation Application, 2022(1): 116-118, 122.
[11]	王宇飞, 李俊娥, 刘艳丽, 等. 容忍阶段性故障的协同网络攻击引发电网级联故障预警方法[J]. 电力系统自动化, 2021, 45(3): 24-32.
	WANG Yufei, LI June, LIU Yanli, et al. Staged failure tolerance based early warning method for cascading failures in power grid caused by coordinated cyber attacks[J]. Automation of Electric Power Systems, 2021, 45(3): 24-32.
[12]	WANG Y F, LIU Y L, LI J E. Deducing cascading failures caused by cyberattacks based on attack gains and cost principle in cyber-physical power systems[J]. Journal of Modern Power Systems and Clean Energy, 2019, 7(6): 1450-1460.
[13]	魏新迟, 董佳, 时珊珊, 等. 基于云模型和随机森林的韧性城市电网风险预警模型[J]. 电力建设, 2024, 45(5): 19-28. doi: 10.12204/j.issn.1000-7229.2024.05.003
	WEI Xinchi, DONG Jia, SHI Shanshan, et al. Enhanced risk warning model for resilient urban power grid using cloud model and random forest[J]. Electric Power Construction, 2024, 45(5): 19-28. doi: 10.12204/j.issn.1000-7229.2024.05.003
[14]	于芃, 程艳, 邢家维, 等. 基于数据驱动的风电机组能效状态检测与预警研究[J]. 山东电力技术, 2024, 51(10): 18-30.
	YU Peng, CHENG Yan, XING Jiawei, et al. Data-driven wind turbine energy efficiency state detection and early warning research[J]. Shandong Electric Power, 2024, 51(10): 18-30.
[15]	任一鸣, 杜董生, 邓祥帅, 等. 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. doi: 10.3969/j.issn.2097-0706.2024.03.007
	REN Yiming, DU Dongsheng, DENG Xiangshuai, et al. Power line fault diagnosis based on GRU and GWO-KELM[J]. Integrated Intelligent Energy, 2024, 46(3): 54-62. doi: 10.3969/j.issn.2097-0706.2024.03.007
[16]	席磊, 彭典名, 曹伟, 等. 数据驱动算法的电力信息物理系统FDIA定位检测[J/OL]. 中国电机工程学报, 2024: 1-12(2024-08-26)[2025-03-01]. https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.240412.
	XI Lei, PENG Dianming, CAO Wei, et al. FDIA location detection of power cyber-physical systems based on data-driven algorithm[J/OL]. Proceedings of the CSEE, 2024: 1-12(2024-08-26)[2025-03-01]. https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.240412.
[17]	杨淇, 陈景文, 华志广, 等. 基于集成型极限学习机的氢燃料电池寿命预测[J]. 电工技术学报, 2025, 40(3): 964-974.
	YANG Qi, CHEN Jingwen, HUA Zhiguang, et al. Research on PEMFC lifetime prediction based on ensemble extreme learning machine[J]. Transactions of China Electrotechnical Society, 2025, 40(3): 964-974.
[18]	徐俊俊, 吴在军, 张腾飞, 等. 融入多源量测数据的配电网分布式区间状态估计[J]. 中国电机工程学报, 2022, 42(24): 8888-8900.
	XU Junjun, WU Zaijun, ZHANG Tengfei, et al. A distributed interval state estimation framework of distribution networks based on multi-source measurements[J]. Proceedings of the CSEE, 2022, 42(24): 8888-8900.
[19]	刘权莹, 李俊娥, 倪明, 等. 电网信息物理系统态势感知: 现状与研究构想[J]. 电力系统自动化, 2019, 43(19): 9-21, 51.
	LIU Quanying, LI June, NI Ming, et al. Situation awareness of grid cyber-physical system: Current status and research ideas[J]. Automation of Electric Power Systems, 2019, 43(19): 9-21, 51.
[20]	于群, 陈佳泰, 曹娜, 等. 基于异质元胞自动机的电力信息物理系统仿真模型[J]. 电力自动化设备, 2025, 45(2): 185-192.
	YU Qun, CHEN Jiatai, CAO Na, et al. Simulation model of cyber-physical power system based on heterogeneous cellular automata[J]. Electric Power Automation Equipment, 2025, 45(2): 185-192.
[21]	杨嘉湜, 黄林, 刘捷, 等. 基于元胞自动机的电力信息物理系统连锁故障仿真分析[J]. 电工电能新技术, 2018, 37(9): 33-41. doi: 10.12067/ATEEE1805005
	YANG Jiashi, HUANG Lin, LIU Jie, et al. Simulation of cascading failure of power cyber-physical system based on cellular automata[J]. Advanced Technology of Electrical Engineering and Energy, 2018, 37(9): 33-41. doi: 10.12067/ATEEE1805005
[22]	唐海国, 张帝, 刘成英, 等. 计及拓扑变换的主动配电网故障风险智能预警[J]. 电力工程技术, 2022, 41(5): 193-201, 226.
	TANG Haiguo, ZHANG Di, LIU Chengying, et al. Intelligent forecast of fault risk in active distribution networks considering network reconfiguration[J]. Electric Power Engineering Technology, 2022, 41(5): 193-201, 226.
[23]	ZHANG Y C, XU Y, DONG Z Y, et al. Intelligent early warning of power system dynamic insecurity risk: Toward optimal accuracy-earliness tradeoff[J]. IEEE Transactions on Industrial Informatics, 2017, 13(5): 2544-2554.
[24]	杨茂, 张书天, 王勃. 基于因果正则化极限学习机的风电功率短期预测方法[J]. 电力系统保护与控制, 2024, 52(11): 127-136.
	YANG Mao, ZHANG Shutian, WANG Bo. Short-term wind power forecasting method based on a causal regularized extreme learning machine[J]. Power System Protection and Control, 2024, 52(11): 127-136.
[25]	夏焰坤, 黄鹏, 任俊杰, 等. 改进蜣螂算法优化混合核极限学习机的系统谐波阻抗估计[J]. 电力系统及其自动化学报, 2024, 36(11): 69-78.
	XIA Yankun, HUANG Peng, REN Junjie, et al. Improved dung beetle optimizer for optimizing hybrid kernel extreme learning machine for system harmonic impedance estimation[J]. Proceedings of the CSU-EPSA, 2024, 36(11): 69-78.
[26]	肖峻, 孙纲, 宋晨辉, 等. 基于安全域的区域综合能源系统安全预警方法[J/OL]. 中国电机工程学报, 2024: 1-15 (2024-08-26)[2025-03-01]. https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.232629.
	XIAO Jun, SUN Gang, SONG Chenhui, et al. A security early warning method based on security region for regional integrated energy system[J/OL]. Proceedings of the CSEE, 2024: 1-15 (2024-08-26)[2025-03-01]. https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.232629.
[27]	姜海洋, 蒋明华, 丁坤, 等. 极端静稳天气事件下电力系统风险评估与管控[J]. 电力系统自动化, 2025, 49(4): 42-52.
	JIANG Haiyang, JIANG Minghua, DING Kun, et al. Risk assessment and control of power system under extreme steady weather events[J]. Automation of Electric Power Systems, 2025, 49(4): 42-52.
[28]	董杰, 宋利明, 黄赟鹏, 等. 含高比例光伏配电网电压安全性数字孪生预警方法[J]. 现代电力, 2023, 40(2): 170-181.
	DONG Jie, SONG Liming, HUANG Yunpeng, et al. A digital twin warning method for voltage security of distribution network containing high proportion of photovoltaic[J]. Modern Electric Power, 2023, 40(2): 170-181.
[29]	黄振宁, 孙宁, 邵华强, 等. 考虑节点惯量的新型电力系统连锁故障仿真模型及关键节点辨识[J]. 山东电力技术, 2024, 51(7): 35-44.
	HUANG Zhenning, SUN Ning, SHAO Huaqiang, et al. Novel power system fault simulation model and key node identification[J]. Shandong Electric Power, 2024, 51(7): 35-44.
[30]	邓燕国, 王冰, 曹智杰, 等. 基于熵权法与GRA-ELM的配电网空间负荷预测[J]. 电力工程技术, 2021, 40(4): 136-141.
	DENG Yanguo, WANG Bing, CAO Zhijie, et al. Spatial load forecasting of distribution network based on entropy weight method and GRA-ELM[J]. Electric Power Engineering Technology, 2021, 40(4): 136-141.
[31]	李晓露, 陈思羽, 柳劲松, 等. 基于数据增强的配电网运行态势预警方法[J]. 电网技术, 2025, 49(3): 1207-1216.
	LI Xiaolu, CHEN Siyu, LIU Jinsong, et al. A method for distribution network operation situation warning based on data augmentation[J]. Power System Technology, 2025, 49(3): 1207-1216.

预警等级	电网状态
0 级（电网安全）	各电网状态处于正常波动范围内
Ⅰ级（蓝色预警）	电网指标超出波动范围，存在安全风险
Ⅱ级（黄色预警）	多个指标超过阈值，电网安全风险较大
Ⅲ级（红色预警）	大范围节点异常、多条线路严重过载、失负荷风险过大

节点	介数中心性	脆弱性指数	综合得分	节点重要性
1	0.12	0.92	0.65	次关键节点
12	0.15	0.85	0.53	次关键节点
18	0.35	0.88	0.82	关键节点
22	0.30	0.80	0.74	关键节点
25	0.28	0.75	0.68	次关键节点

模型	MSE	R²
ELM	0.016 093	0.976 53
BP神经网络	0.017 548	0.974 41
XGBoost	0.028 044	0.959 10
KELM	0.014 082	0.979 46

预警等级	时间段	占比/%
0 级	00:00 — 08:00, 14:00 —16:00， 20:00 — 24:00	66.7
Ⅰ级	09:00 —13:00	20.8
Ⅱ级	17:00 —19:00	12.5
Ⅲ级		0