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

doi:10.11930/j.issn.1004-9649.202311112

摘要/Abstract

摘要：

直流微电网是一个网络物理信息系统，在信息传递的过程中容易遭受网络攻击的影响。虚假数据注入信息通道会影响微电网的系统安全。检测并修正虚假数据注入攻击，能够提升微电网系统运行的安全性。针对这一问题，提出了一种基于卷积神经网络（convolutional neural network，CNN）和长短期记忆网络（long short-term memory，LSTM）联合最大互信息系数（maximum information coefficient，MIC）的二阶段虚假数据注入攻击检测方法。首先，使用CNN从直流微电网运行的时序数列中提取时序特征，运用LSTM模型结合CNN提取的时序特征运行得到直流微电网运行状态预测值，与直流微电网运行的实际值对比，初步判断系统中是否存在虚假数据；其次，考虑到CNN-LSTM模型存在一定的误报率，构建MIC校验器，进一步判断系统中是否存在虚假数据并恢复；最后，通过直流微电网Matlab仿真分析，验证了所提方法的合理性和可行性。

关键词: 直流微电网, 虚假数据注入攻击, 长短期记忆网络, 最大互信息系数

Abstract:

A direct current (DC) microgrid is a cyber-physical information system that is susceptible to network attacks in the process of information transmission. Attackers can impact the security of the microgrid system by injecting false data into the information channel. Detecting and correcting false data injection attacks can enhance the security of the microgrid system operation. To address this issue, a two-stage false data injection attack detection method is proposed based on convolutional neural network (CNN) and long short-term memory (LSTM) combined with maximum information coefficient (MIC). Firstly, the CNN is used to extract the temporal features from the time series data of the DC microgrid operation. And the LSTM model, combined with the temporal features extracted by CNN, is then used to predict the operating state of the DC microgrid. This predicted value is compared with the actual value to preliminarily determine the presence of false data in the system. Secondly, considering the potential false positive rate of the CNN-LSTM model, an MIC verifier is constructed to further determine the presence of false data in the system and restore the data. The rationality and feasibility of the proposed method were verified through Matlab simulation analysis of the DC microgrid.

Key words: DC microgrid, false data injection attack, long short-term memory network, maximum mutual information coefficient

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.

Lei TAO, Pingping LUO, Jikeng LIN. Two-stage Detection Method for DC Microgrid False Data Injection Attack Based on Deep Learning[J]. Electric Power, 2024, 57(9): 11-19.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202311112

https://www.electricpower.com.cn/CN/Y2024/V57/I9/11

图/表 11

图 1 直流微电网控制模型

Fig.1 Control model of DC microgrid

图 2 CNN-LSTM网络模型输入数据结构

Fig.2 Input data structure of CNN-LSTM network model

图 3 CNN-LSTM检测模型流程

Fig.3 Flow chart of CNN-LSTM detection model

图 4 基于CNN-LSTM联合MIC二阶段FDIA检测机制

Fig.4 Two-stage FDIA detection mechanism based on CNN-LSTM combined with MIC

图 5 虚假数据修正模型

Fig.5 False data correction model

图 6 添加负载时的直流微电网电流电压值

Fig.6 The current and voltage value of DC microgrid with load added

图 7 加入虚假数据后的直流微电网电压电流值

Fig.7 The voltage and current value of DC microgrid after adding false data

表 1 攻击前后的MIC值

Table 1 The MIC value before and after the attack

DG	正常运行	负荷变化	FDIA
1	0.92	0.91	0.078
2	0.88	0.88	0.065
3	0.84	0.85	0.080
4	0.89	0.88	0.068

图 8 直流微电网电压电流值

Fig.8 The voltage and current value of DC microgrid

图 9 攻击前后线路电流和母线电压误差

Fig.9 Line current and bus voltage errors before and after the attack

表 2 不同模型的检测结果

Table 2 Test results of different models

检测模型	A/%	P/%	R/%	F/%
BP检测模型	91.62	91.54	91.71	91.63
LSTM检测模型	92.67	93.37	91.87	92.61
二阶段检测模型	94.04	95.29	92.65	93.95

参考文献 23

1	李霞林, 郭力, 王成山, 等. 直流微电网关键技术研究综述[J]. 中国电机工程学报, 2016, 36 (1): 2- 17.
	LI Xialin, GUO Li, WANG Chengshan, et al. Key technologies of DC microgrids: an overview[J]. Proceedings of the CSEE, 2016, 36 (1): 2- 17.
2	刘建伟, 李学斌, 刘晓鸥. 有源配电网中分布式电源接入与储能配置[J]. 发电技术, 2022, 43 (3): 476- 484.
	LIU Jianwei, LI Xuebin, LIU Xiaoou. Distributed power access and energy storage configuration in active distribution network[J]. Power Generation Technology, 2022, 43 (3): 476- 484.
3	周杨, 张俊勃. 适用于孤岛微电网的电压型虚拟同步发电机自适应惯性控制与频率恢复控制[J]. 南方电网技术, 2022, 16 (1): 127- 136.
	ZHOU Yang, ZHANG Junbo. Adaptive inertia control and frequency recovery control of voltage-controlled virtual synchronous generators for an isolated microgrid[J]. Southern Power System Technology, 2022, 16 (1): 127- 136.
4	刘骁康, 王燕舞, 肖江文. 环形直流微电网的二次控制与稳定性分析[J]. 控制理论与应用, 2021, 38 (7): 979- 987.
	LIU Xiaokang, WANG Yanwu, XIAO Jiangwen. Secondary control and stability analysis of ring-bus DC microgrids[J]. Control Theory & Applications, 2021, 38 (7): 979- 987.
5	LAI J G, LU X Q, YU X H, et al. Distributed voltage regulation for cyber-physical microgrids with coupling delays and slow switching topologies[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 50 (1): 100- 110.
6	王波, 张占营, 张霄, 等. 直流微电网分布式储能系统精确电流分配策略[J]. 中国电力, 2022, 55 (8): 96- 103, 112.
	WANG Bo, ZHANG Zhanying, ZHANG Xiao, et al. Accurate current sharing strategy for distributed energy storage system in DC microgrids[J]. Electric Power, 2022, 55 (8): 96- 103, 112.
7	阳育德, 蓝水岚, 覃智君, 等. 电力信息物理融合系统的网络-物理协同攻击[J]. 电力自动化设备, 2020, 40 (2): 97- 103.
	YANG Yude, LAN Shuilan, QIN Zhijun, et al. Coordinated cyber-physical attacks of cyber-physical power system[J]. Electric Power Automation Equipment, 2020, 40 (2): 97- 103.
8	韩丽芳, 胡博文, 杨军, 等. 基于攻击预测的电力CPS安全风险评估[J]. 中国电力, 2019, 52 (1): 48- 56.
	HAN Lifang, HU Bowen, YANG Jun, et al. A new security risk assessment method for cyber physical power system based on attack prediction[J]. Electric Power, 2019, 52 (1): 48- 56.
9	陈郁林, 齐冬莲, 李真鸣, 等. 虚假数据注入攻击下的微电网分布式协同控制[J]. 电力系统自动化, 2021, 45 (5): 97- 103.
	CHEN Yulin, QI Donglian, LI Zhenming, et al. Distributed cooperative control of microgrid under false data injection attacks[J]. Automation of Electric Power Systems, 2021, 45 (5): 97- 103.
10	何耀, 周聪, 郑凌月, 等. 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.
	HE Yao, ZHOU Cong, ZHENG Lingyue, et al. Detection method against false data injection attack based on extended Kalman filter[J]. Electric Power, 2017, 50 (10): 35- 40.
11	ALI B O, JOHNSON TAYLOR T, ALI D. Detection of false-data injection attacks in cyber-physical DC microgrids[J]. IEEE Transactions on Industrial Informatics, 2017, 13 (5): 2693- 2703. DOI
12	王琦, 李梦雅, 汤奕, 等. 电力信息物理系统网络攻击与防御研究综述(一)建模与评估[J]. 电力系统自动化, 2019, 43 (9): 9- 21.
	WANG Qi, LI Mengya, TANG Yi, et al. A review on research of cyber-attacks and defense in cyber physical power systems part one modelling and evaluation[J]. Automation of Electric Power Systems, 2019, 43 (9): 9- 21.
13	GALLO A J, TURAN M S, BOEM F, et al. A distributed cyber-attack detection scheme with application to DC microgrids[J]. IEEE Transactions on Automatic Control, 2020, 65 (9): 3800- 3815. DOI
14	郭方洪, 郑祥康, 邓超, 等. 直流微电网无界虚假数据注入网络攻击检测与系统恢复方法[J]. 电力系统自动化, 2023, 47 (2): 146- 153.
	GUO Fanghong, ZHENG Xiangkang, DENG Chao, et al. Detection and system recovery method against unbounded false data injection network attack on DC microgrid[J]. Automation of Electric Power Systems, 2023, 47 (2): 146- 153.
15	HABIBI M R, BAGHAEE H R, DRAGICEVIC T, et al. Detection of false data injection cyber-attacks in DC microgrids based on recurrent neural networks[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2021, 9 (5): 5294- 5310. DOI
16	HABIBI M R , BAGHAEE H R , DRAGICEVIC T , et al. False data injection cyber-attacks mitigation in parallel DC/DC converters based on artificial neural networks[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2020, PP(99): 1–5.
17	陈亮, 王震, 王刚. 深度学习框架下LSTM网络在短期电力负荷预测中的应用[J]. 电力信息与通信技术, 2017, 15 (5): 8- 11.
	CHEN Liang, WANG Zhen, WANG Gang. Application of LSTM networks in short-term power load forecasting under the deep learning framework[J]. Electric Power Information and Communication Technology, 2017, 15 (5): 8- 11.
18	陈卓, 孙龙祥. 基于深度学习LSTM网络的短期电力负荷预测方法[J]. 电子技术, 2018, 47 (1): 39- 41.
	CHEN Zhuo, SUN Longxiang. Short-term electrical load forecasting based on deep learning LSTM networks[J]. Electronic Technology, 2018, 47 (1): 39- 41.
19	陈铁, 张治藩, 李咸善, 等. 基于混合模态分解和LSTM-CNN的变压器油中溶解气体浓度预测[J]. 中国电力, 2023, 56 (1): 132- 141.
	CHEN Tie, ZHANG Zhifan, LI Xianshan, et al. Prediction of dissolved gas concentration in transformer oil based on hybrid mode decomposition and LSTM-CNN[J]. Electric Power, 2023, 56 (1): 132- 141.
20	GUO F H, XU Q W, WEN C Y, et al. Distributed secondary control for power allocation and voltage restoration in islanded DC microgrids[J]. IEEE Transactions on Sustainable Energy, 2018, 9 (4): 1857- 1869. DOI
21	陆继翔, 张琪培, 杨志宏, 等. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43 (8): 131- 137.
	LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of Electric Power Systems, 2019, 43 (8): 131- 137.
22	ZUO S, ALTUN T, LEWIS F L, et al. Distributed resilient secondary control of DC microgrids against unbounded attacks[J]. IEEE Transactions on Smart Grid, 2020, 11 (5): 3850- 3859. DOI
23	DENG C, GUO F H, WEN C Y, et al. Distributed resilient secondary control for DC microgrids against heterogeneous communication delays and DoS attacks[J]. IEEE Transactions on Industrial Electronics, 2022, 69 (11): 11560- 11568. DOI

[1]	么钟然, 孙丽颖. 考虑线路阻抗的分布式储能SOC均衡控制策略[J]. 中国电力, 2024, 57(9): 238-246.
[2]	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.
[3]	高岩, 吴汉斌, 张纪欣, 张华铭, 张沛. 基于组合深度学习的光伏功率日前概率预测模型[J]. 中国电力, 2024, 57(4): 100-110.
[4]	杨国华, 祁鑫, 贾睿, 刘一峰, 蒙飞, 马鑫, 邢潇文. 基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测[J]. 中国电力, 2024, 57(2): 55-61.
[5]	王锐, 赵学深, 张新慧, 彭克, 许洪璐, 孙浩玥. 基于虚拟惯性参数可行域的直流微电网高频振荡抑制[J]. 中国电力, 2024, 57(10): 123-132.
[6]	李世龙, 李龙江, 刘欣博, 张华. 一种增强稳定性的储能变流器线性自抗扰控制参数整定方法[J]. 中国电力, 2024, 57(10): 25-35.
[7]	邹念, 魏梅芳, 苏盛, 郑应俊, 周文晴. 基于水电关联信息的零电量低压用户窃电检测[J]. 中国电力, 2023, 56(12): 206-216.
[8]	陈铁, 张治藩, 李咸善, 陈一夫, 李鸿鑫. 基于混合模态分解和LSTM-CNN的变压器油中溶解气体浓度预测[J]. 中国电力, 2023, 56(1): 132-141.
[9]	王波, 张占营, 张霄, 席晟哲, 邓锦, 米阳. 直流微电网分布式储能系统精确电流分配策略[J]. 中国电力, 2022, 55(8): 96-103,112.
[10]	张宇, 王洪希, 王璞. 交直流混合微电网互联变流器微分平坦控制[J]. 中国电力, 2022, 55(7): 102-109,120.
[11]	丁雨, 于艾清, 高纯. 基于改进一致性算法的独立光储直流微电网电压稳定能量协调策略[J]. 中国电力, 2022, 55(3): 74-79.
[12]	赵会茹, 赵一航, 郭森. 基于互补集合经验模态分解和长短期记忆神经网络的短期电力负荷预测[J]. 中国电力, 2020, 53(6): 48-55.
[13]	李文明, 苏亮. 园区直流微电网的故障分析及保护配置方案研究[J]. 中国电力, 2019, 52(5): 119-126.
[14]	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.
[15]	张会强，王宇拓，王林川. 基于直流母线电压信号的直流微电网协调控制[J]. 中国电力, 2015, 48(11): 110-116.