Interpretable Detection Method for False Data Injection Attack on Power Grid Based on Multi-head Graph Attention Network and Time Convolution Network Model

SU Xiangjing; DENG Chao; LI Fengyong; FU Yang; XIAO Shiqu

doi:10.7500/AEPS20230410006

您当前的位置：

首页 >

文章列表页 >

Interpretable Detection Method for False Data Injection Attack on Power Grid Based on Multi-head Graph Attention Network and Time Convolution Network Model

Application Research | 更新时间：2025-06-16

- Interpretable Detection Method for False Data Injection Attack on Power Grid Based on Multi-head Graph Attention Network and Time Convolution Network Model
- Automation of Electric Power Systems Vol. 48, Issue 2, Pages: 118-127(2024)
- 作者机构：
  
  1.上海电力大学电气工程学院，上海市 200090
  2.上海电力大学计算机科学与技术学院，上海市 200090
- 作者简介：
- 基金信息：
  
  State Grid Corporation of China(52094022001K);National Natural Science Foundation of China(U2066214)
- DOI：10.7500/AEPS20230410006
  CLC：
- Received：10 April 2023，
  
  Revised：2023-08-15，
  
  Published Online：17 November 2023，
  
  Published：25 January 2024
- 稿件说明：
移动端阅览
苏向敬,邓超,栗风永等.基于MGAT-TCN模型的可解释电网虚假数据注入攻击检测方法[J].电力系统自动化,2024,48(2):118-127.

SU Xiangjing,DENG Chao,LI Fengyong,et al.Interpretable Detection Method for False Data Injection Attack on Power Grid Based on Multi-head Graph Attention Network and Time Convolution Network Model[J].Automation of Electric Power Systems,2024,48(2):118-127.
苏向敬,邓超,栗风永等.基于MGAT-TCN模型的可解释电网虚假数据注入攻击检测方法[J].电力系统自动化,2024,48(2):118-127. DOI： 10.7500/AEPS20230410006.

SU Xiangjing,DENG Chao,LI Fengyong,et al.Interpretable Detection Method for False Data Injection Attack on Power Grid Based on Multi-head Graph Attention Network and Time Convolution Network Model[J].Automation of Electric Power Systems,2024,48(2):118-127. DOI： 10.7500/AEPS20230410006.

摘要

新型电力系统背景下，快速、准确的虚假数据注入攻击(FDIA)检测对电网安全运行至关重要。但现有深度学习方法未能充分挖掘电网量测数据的时序和空间特征信息，影响了模型的检测性能；同时，深度神经网络的“黑盒”属性降低了检测模型的可解释性，导致检测结果缺乏可信度。针对上述问题，提出了一种基于多头图注意力网络和时间卷积网络(MGAT-TCN)模型的可解释电网FDIA检测方法。首先，考虑电网拓扑连接关系与量测数据的空间相关性，引入空间拓扑感知注意力机制，建立多头图注意力网络(MGAT)提取量测数据的空间特征；接着，利用时间卷积网络(TCN)并行提取量测数据的时序特征；最后，在IEEE 14节点系统和IEEE 39节点系统中对所提MGAT-TCN模型进行仿真验证。结果表明，所提模型相比于现有检测模型具有更高的检测准确率和效率，且通过拓扑热力图对注意力权值可视化，实现了模型在空间维度的可解释性。

Abstract

In the background of new power systems

fast and effective detection of false data injection attack (FDIA) is crucial for the safe operation of power grids. However

the existing deep learning methods do not fully explore the spatiotemporal feature information in measurement data of power grids

which affects the detection performance of models. Meanwhile

the “black box” attribute of deep neural networks reduces the interpretability of the detection model

leading to the lack of credibility in detection results. To solve the above problems

an interpretable FDIA detection method is proposed based on multi-head graph attention network and time convolution network (MGAT-TCN) model. First

considering the spatial correlation between power grid topology connection and measurement data

a spatial topology aware attention mechanism is introduced to establish the multi-head graph attention network (MGAT) to extract spatial features of measurement data. Next

the time convolution network (TCN) is used to extract the temporal features of the measurement data in parallel. Finally

the proposed MGAT-TCN model is simulated and validated on the IEEE 14-bus system and IEEE 39-bus system. The results indicate that the proposed model has higher detection accuracy and efficiency compared to the existing detection models

and the visualization of attention weights through topological heat maps can achieve interpretability of the model in spatial dimensions.

关键词

Keywords

references

汤奕，王琦，倪明，等 . 电力信息物理融合系统中的网络攻击分析［J］. 电力系统自动化， 2016 ， 40 （ 6 ）： 148 - 151 .

TANG Yi ， WANG Qi ， Ni Ming ， et al . Analysis of cyber-attacks in cyber physical power system ［J］. Automation of Electric Power Systems ， 2016 ， 40 （ 6 ）： 148 - 151 .

CHEN X L ， HU S L ， LI Y ， et al . Co-estimation of state and FDI attacks and attack compensation control for multi-area load frequency control systems under FDI and DoS attacks ［J］. IEEE Transactions on Smart Grid ， 2022 ， 13 （ 3 ）： 2357 - 2368 .

陈凡，史杰，刘海涛，等 . 考虑负荷重分配攻击和脆弱线路防御的发输电系统可靠性评估［J］. 电力系统自动化， 2022 ， 46 （ 2 ）： 65 - 72 .

CHEN Fan ， SHI Jie ， LIU Haitao ， et al . Reliability evaluation of power generation and transmission system considering load redistribution attack and defense of vulnerable line ［J］. Automation of Electric Power Systems ， 2022 ， 46 （ 2 ）： 65 - 72 .

GAO S B ， HE Z L ， WEI X G ， et al . Bilevel model for protection-branch measurements-based topology attack against DC and AC state estimations ［J］. IEEE Systems Journal ， 2022 ， 16 （ 4 ）： 5369 - 5379 .

MUKHERJEE D . Data-driven false data injection attack： a low-rank approach ［J］. IEEE Transactions on Smart Grid ， 2022 ， 13 （ 3 ）： 2479 - 2482 .

彭莎，孙铭阳，张镇勇，等 . 机器学习在电力信息物理系统网络安全中的应用［J］. 电力系统自动化， 2022 ， 46 （ 9 ）： 200 - 215 .

PENG Sha ， SUN Mingyang ， ZHANG Zhenyong ， et al . Applications of machine learning in cyber security of cyber-physical power system ［J］. Automation of Electric Power Systems ， 2022 ， 46 （ 9 ）： 200 - 215 .

JORJANI M ， SEIFI H ， VARJANI A Y . A graph theory-based approach to detect false data injection attacks in power system AC state estimation ［J］. IEEE Transactions on Industrial Informatics ， 2021 ， 17 （ 4 ）： 2465 - 2475 .

PARIZAD A ， HATZIADONIU C J . Cyber-attack detection using principal component analysis and noisy clustering algorithms： a collaborative machine learning-based framework ［J］. IEEE Transactions on Smart Grid ， 2022 ， 13 （ 6 ）： 4848 - 4861 .

黄冬梅，何立昂，孙锦中，等 . 基于边缘计算的电网假数据攻击分布式检测方法［J］. 电力系统保护与控制， 2021 ， 49 （ 13 ）： 1 - 9 .

HUANG Dongmei ， HE Li’ang ， SUN Jinzhong ， et al . Distribution detection method for a false data attack in a power grid based on edge computing ［J］. Power System Protection and Control ， 2021 ， 49 （ 13 ）： 1 - 9 .

陈冰，唐永旺 . 基于Transformer编码器的智能电网虚假数据注入攻击检测［J］. 计算机应用与软件， 2022 ， 39 （ 7 ）： 336 - 342 .

CHEN Bing ， TANG Yongwang . False data injection attacks detecting based on Transformer encoder in smart grid ［J］. Computer Applications and Software ， 2022 ， 39 （ 7 ）： 336 - 342 .

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 .

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 Jie ， 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 .

BOYACI O ， NARIMANI M R ， DAVIS K R ， et al . Joint detection and localization of stealth false data injection attacks in smart grids using graph neural networks ［J］. IEEE Transactions on Smart Grid ， 2022 ， 13 （ 1 ）： 807 - 819 .

LI X P ， WANG Y K ， LU Z G . Graph-based detection for false data injection attacks in power grid ［J］. Energy ， 2023 ， 263 ： 125865 .

BITIRGEN K ， FILIK Ü B . A hybrid deep learning model for discrimination of physical disturbance and cyber-attack detection in smart grid ［J］. International Journal of Critical Infrastructure Protection ， 2023 ， 40 ： 100582 .

DRAYER E ， ROUTTENBERG T . Detection of false data injection attacks in smart grids based on graph signal processing ［J］. IEEE Systems Journal ， 2020 ， 14 （ 2 ）： 1886 - 1896 .

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/OL］. 中国电机工程学报［ 2023-01-15 ］. https：//kns.cnki.net/kcms2/article/abstract？v=3uoqIhG8C45S0n9fL2suRadTyEVl2pW9UrhTDCdPD65djwFi6aRxPXWWapzWMhQJp16xGpKxBqlv7m6hMvRSeMxp3omO7IRN&uniplatform=NZKPT https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C45S0n9fL2suRadTyEVl2pW9UrhTDCdPD65djwFi6aRxPXWWapzWMhQJp16xGpKxBqlv7m6hMvRSeMxp3omO7IRN&uniplatform=NZKPT .

YANG Yuze ， LIU Wenxia ， LI Chengze ， et al . Review of FDIA detection methods for electric power SCADA system ［J/OL］. Proceedings of the CESS ［ 2023-01-15 ］. https：//kns.cnki.net/kcms2/article/abstract？v=3uoqIhG8C45S0n9fL2suRa dTyEVl2pW9UrhTDCdPD65djwFi6aRxPXWWapzWMhQJp16xGpKxBqlv7m6hMvRSeMxp3omO7IRN&uniplatform=NZKPT https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C45S0n9fL2suRadTyEVl2pW9UrhTDCdPD65djwFi6aRxPXWWapzWMhQJp16xGpKxBqlv7m6hMvRSeMxp3omO7IRN&uniplatform=NZKPT .

蒲天骄，乔骥，赵紫璇，等 . 面向电力系统智能分析的机器学习可解释性方法研究（一）：基本概念与框架［J/OL］. 中国电机工程学报［ 2023-01-15 ］. https：//kns.cnki.net/kcms2/article/abstract？v=3uoqIhG8C45S0n9fL2suRadTyEVl2pW9UrhTD CdPD65djwFi6aRxPY3uWaSWgx2XKpwR_LTG6Hzf51sIGn6SiOnFd1TdSiHT&uniplatform=NZKPT https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C45S0n9fL2suRadTyEVl2pW9UrhTDCdPD65djwFi6aRxPY3uWaSWgx2XKpwR_LTG6Hzf51sIGn6SiOnFd1TdSiHT&uniplatform=NZKPT .

PU Tianjiao ， QIAO Ji ， ZHAO Zixuan ， et al . Research on interpretable methods of machine learning applied in intelligent analysis of power system （Part 1 ）： basic concept and framework［J/OL］. Proceedings of the CSEE ［ 2023-01-15 ］. https：//kns.cnki.net/kcms2/article/abstract？v=3uoqIhG8C45S0n9fL2su RadTyEVl2pW9UrhTDCdPD65djwFi6aRxPY3uWaSWgx2XKpwR_LTG6Hzf51sIGn6SiOnFd1TdSiHT&uniplatform=NZKPT https://kns.cnki.net/kcms2/article/abstract?v=3uoqIhG8C45S0n9fL2suRadTyEVl2pW9UrhTDCdPD65djwFi6aRxPY3uWaSWgx2XKpwR_LTG6Hzf51sIGn6SiOnFd1TdSiHT&uniplatform=NZKPT .

SU X J ， SHAN Y H ， LI C J ， et al . Spatial-temporal attention and GRU based interpretable condition monitoring of offshore wind turbine gearboxes ［J］. IET Renewable Power Generation ， 2022 ， 16 （ 2 ）： 402 - 415 .

苏向敬，周汶鑫，李超杰，等 . 基于双重注意力LSTM神经网络的可解释海上风电出力预测［J］. 电力系统自动化， 2022 ， 46 （ 7 ）： 141 - 151 .

SU Xiangjing ， ZHOU Wenxin ， LI Chaojie ， et al . Interpretable offshore wind power output forecasting based on long short-term memory neural network with dual-stage attention ［J］. Automation of Electric Power Systems ， 2022 ， 46 （ 7 ）： 141 - 151 .

赵丽莉，刘忠喜，孙国强，等 . 基于非线性状态估计的虚假数据注入攻击代价分析［J］. 电力系统保护与控制， 2019 ， 47 （ 19 ）： 38 - 45 .

ZHAO Lili ， LIU Zhongxi ， SUN Guoqiang ， et al . Cost analysis of the false data injection attack based on nonlinear state estimation ［J］. Power System Protection and Control ， 2019 ， 47 （ 19 ）： 38 - 45 .

LIU Y ， NING P ， REITER M K . False data injection attacks against state estimation in electric power grids ［J/OL］. ACM Transaction on Information and System Security ［ 2023-01-15 ］. https：//dl.acm.org/doi/10.1145/1952982.1952995 https://dl.acm.org/doi/10.1145/1952982.1952995 .

纪守领，李进锋，杜天宇，等 . 机器学习模型可解释性方法、应用与安全研究综述［J］. 计算机研究与发展， 2019 ， 56 （ 10 ）： 2071 - 2096 .

JI Shouling ， LI Jinfeng ， DU Tianyu ， et al . Survey on techniques， applications and security of machine learning interpretability ［J］. Journal of Computer Research and Development ， 2019 ， 56 （ 10 ）： 2071 - 2096 .

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 .

黄崇鑫，洪明磊，伏帅，等 . 考虑虚假数据注入攻击的有源配电网分布式状态估计［J］. 电力工程技术， 2022 ， 41 （ 3 ）： 22 - 31 .

HUANG Chongxin ， HONG Minglei ， FU Shuai ， et al . Distributed state estimation of active distribution network considering false data injection attack ［J］. Electric Power Engineering Technology ， 2022 ， 41 （ 3 ）： 22 - 31 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Ultra-short-term Regional Load Forecasting Based on Spatio-Temporal Graph Attention Network

Interpretable Power Output Prediction of Multiple Wind Turbines for Offshore Wind Farm Based on Multiple Spatio-temporal Attention Graph Neural Network Model

Transient Frequency Safety Assessment Based on Independent Spatial-temporal Feature Extraction and Grouped Enhancement

Related Author

ZHAO Ziyu

CHEN Yuanrui

CHEN Tingwei

LIU Junfeng

ZENG Jun

NIE Liangzhao

LI Chaojie

MI Yang

Related Institution

School of Electric Power Engineering, South China University of Technology

School of Automation Science and Engineering, South China University of Technology

School of Electrical Engineering and Telecommunications, University of New South Wales

School of Electrical and Electronic Engineering, Nanyang Technological University

National Joint Engineering Laboratory of Power Grid with Electric Vehicles (Shandong University)

⁰