基于反向鲸鱼-多隐层极限学习机的电网FDIA检测

doi:10.11930/j.issn.1004-9649.202309029

中国电力 ›› 2024, Vol. 57 ›› Issue (9): 20-31.DOI: 10.11930/j.issn.1004-9649.202309029

• 面向电力基础设施的跨域攻击威胁与防御 • 上一篇下一篇

基于反向鲸鱼-多隐层极限学习机的电网FDIA检测

席磊¹^,²(), 王艺晓¹(), 何苗³, 程琛¹, 田习龙¹

1. 三峡大学电气与新能源学院，湖北宜昌　443002
2. 梯级水电站运行与控制湖北省重点实验室（三峡大学），湖北宜昌　443002
3. 国网荆州供电公司变电运维分公司，湖北荆州　434000

收稿日期:2023-09-07 接受日期:2024-02-04 出版日期:2024-09-28 发布日期:2024-09-23
作者简介:席磊（1982—），男，通信作者，教授，从事电力系统运行与控制、自动发电控制、信息物理系统网络攻击与防御、智能控制方法研究，E-mail：xilei2014@163.com
王艺晓（2000—），女，硕士研究生，从事信息物理系统网络攻击与防御研究，E-mail：wangyx169@163.com
基金资助:
国家自然科学基金资助项目（高比例大容量新能源接入的新型电力系统自动发电控制全局类脑分布协同理论与方法研究，52277108）。

FDIA Detection in Power Grid Based on Opposition-Based Whale Optimization Algorithm and Multi-layer Extreme Learning Machine

Lei XI¹^,²(), Yixiao WANG¹(), Miao HE³, Chen CHENG¹, Xilong TIAN¹

1. College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China
2. Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station (China Three Gorges University), Yichang 443002, China
3. Substation and Operation Branch of State Grid Jingzhou Electric Power Supply Company, Jingzhou 434000, China

Received:2023-09-07 Accepted:2024-02-04 Online:2024-09-28 Published:2024-09-23
Supported by:
This work is supported by National Natural Science Foundation of China (Study on Automatic Generation Control with Global Brain-Like Distributed Cooperative Theory and Method for New Power System with the Access of High Proportion and Large Capacity of New Energy, No.52277108)

摘要/Abstract

摘要：

针对目前已有的电力信息物理系统虚假数据注入攻击检测方法由于特征表达能力有限，而导致无法精确获取受攻击位置的问题，提出一种基于反向学习鲸鱼优化多隐层极限学习机的虚假数据注入攻击定位检测方法。所提方法不仅将极限学习机拓展为多隐层神经网络，解决其特征表达能力有限的问题，而且引入鲸鱼优化算法对多隐层极限学习机的各隐层神经元个数进行寻优并采用反向学习策略提高其收敛速度和检测精度，以防止随机确定各隐层神经元个数对检测方法的泛化性能和定位检测结果造成影响。通过在不同场景下对IEEE-14和57节点测试系统进行大量实验，验证了所提方法能够通过历史数据自动识别受攻击的系统状态量所对应的精确位置。与其他多种方法相比，所提方法具有更优的精度、召回率和F1值。

关键词: 电力信息物理系统, 虚假数据注入攻击, 多隐层极限学习机, 鲸鱼优化, 反向学习

Abstract:

At present, the existing false data injection attack (FDIA) detection methods for cyber-physical power system can not precisely obtain the location of the attack due to its limited ability of feature expression. Therefore, this paper proposes a FDIA location detection method based on opposition-based learning whale optimization algorithm and multi-layer extreme learning machine (OWOA-ELM^ML). The proposed method not only extends the extreme learning machine into a multi-layer neural network to solve the problem of its limited ability of feature expression, but also introduces the whale optimization algorithm to optimize the number of neurons of the multi-layer extreme learning machine, and uses the opposition-based learning strategy to improve its convergence speed and detection accuracy so as to prevent the influence of randomly determining the number of neurons in each hidden layer on the generalization performance and location detection results of the detection method. Through a large number of simulation tests on IEEE-14 and 57-bus test systems under different scenarios, it is verified that the proposed method can automatically identify the exact position of the attacked system state through the historical data. Compared with other comparative methods, the proposed method has better precision, recall rate and F1 value.

Key words: cyber-physical power system, false data injection attack, multi-layer extreme learning machine, whale optimization algorithm, opposition-based learning

席磊, 王艺晓, 何苗, 程琛, 田习龙. 基于反向鲸鱼-多隐层极限学习机的电网FDIA检测[J]. 中国电力, 2024, 57(9): 20-31.

Lei XI, Yixiao WANG, Miao HE, Chen CHENG, Xilong TIAN. FDIA Detection in Power Grid Based on Opposition-Based Whale Optimization Algorithm and Multi-layer Extreme Learning Machine[J]. Electric Power, 2024, 57(9): 20-31.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202309029

https://www.electricpower.com.cn/CN/Y2024/V57/I9/20

图/表 16

图 1 CPPS结构

Fig.1 The structure of CPPS

图 2 基于ELMML的FDIA定位检测数学模型

Fig.2 The mathematical model of FDIA location detection based on ELMML

图 3 测试集定位检测结果

Fig.3 Location detection result of the test set

图 4 OWOA-ELMML检测方法流程

Fig.4 The flow chart of OWOA-ELMML detection method

图 5 IEEE-14和57节点测试系统拓扑

Fig.5 The topology of IEEE-14 and 57-bus test system

图 6 IEEE-14和57节点测试系统攻击前后最大归一化残差

Fig.6 The largest normalized residual before and after the attack on the IEEE-14 and 57-bus test system

图 7 IEEE-14和57节点测试系统攻击前后量测数据

Fig.7 Measurement data before and after the attack on the IEEE-14 and 57-bus test system

图 8 IEEE-14和57节点测试系统攻击前后状态量

Fig.8 State data before and after the attack on the IEEE-14 and 57-bus test system

表 1 混淆矩阵

Table 1 Confusion matrix

	预测值正类	预测值负类
真实值正类	真正类（ture positive，T_P）	假负类（false negative，F_n）
真实值负类	假正类（false positive，F_P）	真负类（ture negative，T_n）

图 9 IEEE-14节点测试系统各节点定位检测准确率

Fig.9 Location detection accuracy for each bus of the IEEE-14 bus test system

表 2 IEEE-14节点测试系统定位检测指标结果

Table 2 The location detection index results of the IEEE-14 bus test system

指标	精度	召回率	F1值
OWOA-ELM^ML	0.9836	0.9684	0.9759
WOA-ELM^ML	0.9765	0.9628	0.9696
ELM^ML	0.9774	0.9571	0.9671
DBN-ELM	0.9707	0.9402	0.9552
CNN	0.9709	0.9295	0.9497
ELM	0.9499	0.9020	0.9253
SVM	0.9595	0.8461	0.8992

图 10 IEEE-14节点测试系统ROC曲线

Fig.10 ROC curves of the IEEE-14 bus test system

图 11 IEEE-57节点测试系统各节点定位检测准确率

Fig.11 Location detection accuracy for each bus of the IEEE-57 bus test system

表 3 IEEE-57节点测试系统定位检测指标结果

Table 3 The location detection index results of the IEEE-57 bus test system

指标	精度	召回率	F1值
OWOA-ELM^ML	0.9527	0.9299	0.9411
WOA-ELM^ML	0.9302	0.9020	0.9159
ELM^ML	0.9314	0.8946	0.9126
DBN-ELM	0.8991	0.8173	0.8563
CNN	0.8875	0.8123	0.8482
ELM	0.8857	0.8068	0.8444
SVM	0.9028	0.7544	0.8220

图 12 IEEE-57节点测试系统ROC曲线

Fig.12 ROC curves of the IEEE-57 bus test system

表 4 各检测方法的训练与测试耗时

Table 4 The training and testing time of each testing method 单位：s

检测方法	IEEE-14节点测试系统		IEEE-57节点测试系统
检测方法	训练用时	测试用时	训练用时	测试用时
ELM^ML	0.20576	0.00621	0.25172	0.01067
DBN-ELM	1.04498	0.00901	1.27239	0.01726
CNN	13.97473	0.01049	21.00797	0.02125
SVM	2.27905	0.00863	18.71482	0.02322

参考文献 39

1	何瑞文, 龙隆, 张宝仁, 等. 电力信息物理系统中信息系统物理化的建模及分析方法[J]. 中国电机工程学报, 2024, 44 (1): 72- 85.
	HE Ruiwen, LONG Long, ZHANG Baoren, et al. Cyber system physicalizing modeling and analysis method in cyber-physical power systems[J]. Proceedings of the CSEE, 2024, 44 (1): 72- 85.
2	李晓, 许剑冰, 李满礼, 等. 考虑信息失效影响的配电网信息物理系统安全性评估方法[J]. 中国电力, 2022, 55 (2): 73- 81.
	LI Xiao, XU Jianbing, LI Manli, et al. A security evaluation method for cyber physical distribution system considering influence of information failure[J]. Electric Power, 2022, 55 (2): 73- 81.
3	姚鹏超, 颜秉晶, 郝唯杰, 等. 电力信息物理系统入侵容忍能力评估方法[J]. 中国电力, 2022, 55 (4): 13- 22.
	YAO Pengchao, YAN Bingjing, HAO Weijie, et al. An intrusion tolerance assessment method for cyber-physical power system[J]. Electric Power, 2022, 55 (4): 13- 22.
4	李欣, 易柳含, 刘晨凯, 等. 基于数据驱动的电力系统虚假数据注入攻击检测[J]. 智慧电力, 2023, 51 (2): 30- 37.
	LI Xin, YI Liuhan, LIU Chenkai, et al. False data injection attacks detection in power system based on data-driven algorithm[J]. Smart Power, 2023, 51 (2): 30- 37.
5	YANG Jun, ZHANG Wenan, GUO Fanghong. Distributed kalman-like filtering and bad data detection in the large-scale power system[J]. IEEE Transactions on Industrial Informatics, 2022, 18 (8): 5096- 5104. DOI
6	ZHOU T L, XIAHOU K S, ZHANG L L, et al. Real-time detection of cyber-physical false data injection attacks on power systems[J]. IEEE Transactions on Industrial Informatics, 2021, 17 (10): 6810- 6819. DOI
7	MUSLEH A S, CHEN G, DONG Z Y. A survey on the detection algorithms for false data injection attacks in smart grids[J]. IEEE Transactions on Smart Grid, 2020, 11 (3): 2218- 2234. DOI
8	KHALAF M, YOUSSEF A, EL-SAADANY E. Joint detection and mitigation of false data injection attacks in AGC systems[J]. IEEE Transactions on Smart Grid, 2019, 10 (5): 4985- 4995. DOI
9	YAN J J, YANG G H, WANG Y. Dynamic reduced-order observer-based detection of false data injection attacks with application to smart grid systems[J]. IEEE Transactions on Industrial Informatics, 2022, 18 (10): 6712- 6722. DOI
10	ZHANG Y, WANG J H, CHEN B. Detecting false data injection attacks in smart grids: a semi-supervised deep learning approach[J]. IEEE Transactions on Smart Grid, 2021, 12 (1): 623- 634. DOI
11	OZAY M, ESNAOLA I, YARMAN VURAL F T, et al. Machine learning methods for attack detection in the smart grid[J]. IEEE Trans Neural Netw Learn Syst, 2016, 27 (8): 1773- 1786. DOI
12	CAMANA A M R, AHMED S, GARCIA C E, et al. Extremely randomized trees-based scheme for stealthy cyber-attack detection in smart grid networks[J]. IEEE Access, 2020, 8, 19921- 19933. DOI
13	WANG D F, WANG X J, ZHANG Y, et al. Detection of power grid disturbances and cyber-attacks based on machine learning[J]. Journal of Information Security and Applications, 2019, 46, 42- 52. DOI
14	KURT M N, OGUNDIJO O, LI C, et al. Online cyber-attack detection in smart grid: a reinforcement learning approach[J]. IEEE Transactions on Smart Grid, 2019, 10 (5): 5174- 5185. DOI
15	HE Y B, MENDIS G J, WEI J. Real-time detection of false data injection attacks in smart grid: a deep learning-based intelligent mechanism[J]. IEEE Transactions on Smart Grid, 2017, 8 (5): 2505- 2516. DOI
16	郑瑶, 张颉, 姚文轩, 等. 基于空间特征的电网同步量测虚假数据注入攻击检测[J]. 电力系统自动化, 2023, 47 (10): 128- 134.
	ZHENG Yao, ZHANG Xie, YAO Wenxuan, et al. Spatial feature based detection of false data injection attack on synchronous grid measurements[J]. Automation of Electric Power Systems, 2023, 47 (10): 128- 134.
17	WU Ting, XUE Wenli, WANG Huaizhi, et al. Extreme learning machine-based state reconstruction for automatic attack filtering in cyber physical power system[J]. IEEE Transactions on Industrial Informatics, 2021, 17 (3): 1892- 1904. DOI
18	KASUN L, ZHOU H, HUNG G B, VONG C M. Representational learning with ELMs for big data. IEEE Intelligent Systems, 2013, 28(6): 31−34.
19	文云峰, 赵荣臻, 肖友强, 等. 基于多层极限学习机的电力系统频率安全评估方法[J]. 电力系统自动化, 2019, 43 (1): 133- 140.
	WEN Yunfeng, ZHAO Rongzhen, XIAO Youqiang, et al. Frequency safety assessment of power system based on multi-layer extreme learning machine[J]. Automation of Electric Power Systems, 2019, 43 (1): 133- 140.
20	ZHAO X L, JIA M P, BIN J C, et al. Multiple-order graphical deep extreme learning machine for unsupervised fault diagnosis of rolling bearing[J]. IEEE Transactions on Instrumentation Measurement, 2021, 70, 3041087.
21	MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95, 51- 67. DOI
22	杨玉泽, 刘文霞, 李承泽, 等. 面向电力SCADA系统的FDIA检测方法综述[J]. 中国电机工程学报, 2023, 43 (22): 8602- 8622.
	YANG Yuze, LIU Wenxia, LI Chengze, et al. Review of FDIA detection methods for electric power SCADA system[J]. Proceedings of the CSEE, 2023, 43 (22): 8602- 8622.
23	PAL S, SIKDAR B, CHOW J H. Classification and detection of PMU data manipulation attacks using transmission line parameters[J]. IEEE Transactions on Smart Grid, 2018, 9 (5): 5057- 5066. DOI
24	DENG R L, XIAO G X, LU R X, et al. False data injection on state estimation in power systems—attacks, impacts, and defense: a survey[J]. IEEE Transactions on Industrial Informatics, 2017, 13 (2): 411- 423. DOI
25	LIANG G Q, ZHAO J H, LUO F J, et al. A review of false data injection attacks against modern power systems[J]. IEEE Transactions on Smart Grid, 2017, 8 (4): 1630- 1638. DOI
26	YANG Q Y, YANG J, YU W, et al. On false data-injection attacks against power system state estimation: modeling and countermeasures[J]. IEEE Transactions on Parallel and Distributed Systems, 2014, 25 (3): 717- 729. DOI
27	WANG S Y, BI S Z, ZHANG Y J A. Locational detection of the false data injection attack in a smart grid: a multilabel classification approach[J]. IEEE Internet of Things Journal, 2020, 7 (9): 8218- 8227. DOI
28	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70 (1/2/3): 489- 501.
29	ASHRAFUZZAMAN M, DAS S, CHAKHCHOUKH Y, et al. Detecting stealthy false data injection attacks in the smart grid using ensemble-based machine learning[J]. Computers & Security, 2020, 97, 101994.
30	ABO-ELYOUSR F K, ABDELAZIZ A Y. A novel modified robust load frequency control for mass-less inertia photovoltaics penetrations via hybrid PSO-WOA approach[J]. Electric Power Components and Systems, 2019, 47 (19/20): 1744- 1758.
31	张国治, 陈康, 方荣行, 等. 基于DGA与鲸鱼算法优化LogitBoost-决策树的变压器故障诊断方法[J]. 电力系统保护与控制, 2023, 51 (7): 63- 72.
	ZHANG Guozhi, CHEN Kang, FANG Rongxing, et al. Transformer fault diagnosis based on DGA and a whale algorithm optimizing a LogitBoost-decision tree[J]. Power System Protection and Control, 2023, 51 (7): 63- 72.
32	ALZAIDI K M S, BAYAT O, UÇAN O N. Multiple DGs for reducing total power losses in radial distribution systems using hybrid WOA-SSA algorithm[J]. International Journal of Photoenergy, 2019, 2019, 2426538.
33	TIZHOOSH H R. Opposition-based learning: a new scheme for machine intelligence[C]//Proceedings of the International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06). ACM, 2005: 95–701.
34	郝少飞, 邹文进, 葛浩然, 等. 基于改进鲸鱼优化算法的微电网优化运行[J]. 广东电力, 2022, 35 (1): 51- 59.
	HAO Shaofei, ZOU Wenjin, GE Haoran, et al. Optimizing operation of microgrid based on improved whale optimization algorithm[J]. Guangdong Electric Power, 2022, 35 (1): 51- 59.
35	黄欣, 赵敏彤, 郇嘉嘉, 等. 基于BWO-DBSCAN和CSA-OCRKELM的变电站数据流异常检测方法[J]. 广东电力, 2023, 36 (5): 39- 48.
	HUANG Xin, ZHAO Mintong, HUAN Jiajia, et al. Research on anomaly detection method of substation data flow based on BWO-DBSCAN and CSA-OCRKELM[J]. Guangdong Electric Power, 2023, 36 (5): 39- 48.
36	李元诚, 曾婧. 基于改进卷积神经网络的电网假数据注入攻击检测方法[J]. 电力系统自动化, 2019, 43 (20): 97- 104.
	LI Yuancheng, ZENG Jing. Detection method of false data injection attack on power grid based on improved convolutional neural network[J]. Automation of Electric Power Systems, 2019, 43 (20): 97- 104.
37	席磊, 何苗, 周博奇, 等. 基于改进多隐层极限学习机的电网虚假数据注入攻击检测[J]. 自动化学报, 2023, 49 (4): 881- 890.
	XI Lei, HE Miao, ZHOU Boqi, et al. Research on false data injection attack detection in power system based on improved multi layer extreme learning machine[J]. Acta Automatica Sinica, 2023, 49 (4): 881- 890.
38	胡聪, 洪德华, 张翠翠, 等. 一种基于特征映射与深度学习的虚假数据注入检测方法[J]. 现代电力, 2023, 40 (1): 125- 132.
	HU Cong, HONG Dehua, ZHANG Cuicui, et al. A method to detect false data injection based on feature mapping and deep learning[J]. Modern Electric Power, 2023, 40 (1): 125- 132.
39	XUE D B, JING X R, LIU H Q. Detection of false data injection attacks in smart grid utilizing ELM-based OCON framework[J]. IEEE Access, 2019, 7, 31762- 31773. DOI

[1]	陶磊, 罗萍萍, 林济铿. 基于深度学习的直流微电网虚假数据注入攻击二阶段检测方法[J]. 中国电力, 2024, 57(9): 11-19.
[2]	徐峰亮, 王克谦, 王文豪, 王鹏, 王文烨, 张帅, 赵凤展. 计及激励型需求响应的低压配电网混合储能优化配置[J]. 中国电力, 2024, 57(6): 90-101.
[3]	马宏忠, 宣文婧, 朱沐雨, 陈悦林. 基于LWOA-LSTM的大容量锂电池SOC估计[J]. 中国电力, 2024, 57(6): 37-44.
[4]	陈正雄, 帕孜来·马合木提, 沈玮. 基于改进支持向量回归的IGBT老化预测[J]. 中国电力, 2022, 55(7): 1-10.
[5]	姚鹏超, 颜秉晶, 郝唯杰, 杨强. 电力信息物理系统入侵容忍能力评估方法[J]. 中国电力, 2022, 55(4): 13-22.
[6]	万克厅, 陆玲霞, 于淼, 齐冬莲. 基于多组件并行架构的电力CPS实时联合仿真平台[J]. 中国电力, 2022, 55(2): 51-61.
[7]	周鑫, 林镜星, 谢志炜, 张铮, 梁濡铎, 欧祖宏. 基于数据增强及降维方法的配网业扩工程分类模型[J]. 中国电力, 2022, 55(12): 91-97.
[8]	彭春华, 刘懿, 孙惠娟. 计及条件风险成本的含EH-CSP电站多源发电系统优化运行[J]. 中国电力, 2022, 55(1): 64-74.
[9]	赵宏大, 陈琛, 王哲, 王海勇. 电力CPS环境下电力4G无线专网向5G演进策略[J]. 中国电力, 2021, 54(3): 68-79.
[10]	张少明, 盛四清. 基于改进粒子群算法的微网优化运行[J]. 中国电力, 2020, 53(5): 24-31.
[11]	曹生让, 丁晓群, 王庆燕, 张静. 基于反向云自适应粒子群算法的多目标无功优化[J]. 中国电力, 2018, 51(7): 21-27.
[12]	何耀, 周聪, 郑凌月, 张维锡, 谢育轩. 基于扩展卡尔曼滤波的虚假数据攻击检测方法[J]. 中国电力, 2017, 50(10): 35-40.

基于反向鲸鱼-多隐层极限学习机的电网FDIA检测

FDIA Detection in Power Grid Based on Opposition-Based Whale Optimization Algorithm and Multi-layer Extreme Learning Machine

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 39

相关文章 12

编辑推荐

Metrics

模态框（Modal）标题

基于反向鲸鱼-多隐层极限学习机的电网FDIA检测

FDIA Detection in Power Grid Based on Opposition-Based Whale Optimization Algorithm and Multi-layer Extreme Learning Machine

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 39

相关文章 12

编辑推荐

Metrics