A Novel Detection Method for False Data Injection Attacks in Power Systems Based on CPO-CNN-SE

LI Zewu; YANG Shan; GAO Zhirong; LUO Zhaoxu

doi:10.20204/j.sp.2026.04013

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

A Novel Detection Method for False Data Injection Attacks in Power Systems Based on CPO-CNN-SE

更新时间：2026-04-20

- A Novel Detection Method for False Data Injection Attacks in Power Systems Based on CPO-CNN-SE
- Vol. 54, Issue 4, Pages: 103-110(2026)
- 作者机构：
  
  （湖南工业大学交通与电气工程学院，）,湖南,株洲,412007
- 作者简介：
- 基金信息：
- DOI：10.20204/j.sp.2026.04013
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
李泽武,杨杉,高芷蓉,罗朝旭.基于CPO-CNN-SE的新型电力系统虚假数据注入攻击检测方法[J].智慧电力,2026,54(4):103-110.

doi:10.20204/j.sp.2026.04013
李泽武,杨杉,高芷蓉,罗朝旭.基于CPO-CNN-SE的新型电力系统虚假数据注入攻击检测方法[J].智慧电力,2026,54(4):103-110. DOI： 10.20204/j.sp.2026.04013.

doi:10.20204/j.sp.2026.04013 DOI：

摘要

新型电力系统的虚假数据注入攻击（FDIA）检测亟需兼顾准确性与实时性。为同步提升检测精度与速度，提出一种基于冠豪猪算法优化压缩激励卷积神经网络（CPO-CNN-SE）的检测方法。针对人工选取卷积神经网络（CNN）超参数难以获得最优配置的问题，该方法利用冠豪猪优化算法（CPO）进行超参数寻优，从而提升CNN检测模型的精度。同时，为满足FDIA检测速度的提升需求，引入压缩激励注意力机制（SE）构建基于CNN-SE的混合学习模型，以增强CNN对FDIA空间特征的表征效率。仿真结果表明，所提方法能够精准且快速地检测FDIA，可为提升新型电力系统在面对复杂网络攻击时的态势感知能力与防御韧性提供重要的技术支撑。

Abstract

The detection of false data injection attacks (FDIA) in new-type power systems urgently requires a balance between accuracy and real-time performance. To simultaneously improve detection precision and speed

this paper proposes a detection method based on a crown porcupine algorithm-optimized squeeze-and-excitation convolutional neural network (CPO-CNN-SE). Aiming at the problem that manual selection of hyperparameters for convolutional neural networks (CNN) often fails to achieve optimal configuration

the method utilizes the crown porcupine optimizer (CPO) to perform hyperparameter tuning

thereby enhancing the accuracy of the CNN detection model. Meanwhile

to meet the demand for faster FDIA detection

a squeeze-and-excitation (SE) attention mechanism is introduced to construct a hybrid learning model based on CNN-SE

which strengthens the CNN’s efficiency in representing spatial features of FDIA. Simulation results demonstrate that the proposed method can accurately and rapidly detect FDIA

providing important technical support for improving situational awareness and defense resilience of new-type power systems under complex cyberattacks.

关键词

Keywords

references

尹莞婷，王嘉杰，王智敏，等. 典型极端气候下电网未来态调度的数字化效果 [J ] .电网与清洁能源，2025，41（10）：1-13.

张凯瑞，明昊，高赐威. 基于CPSS视角的需求响应能力评估综述 [J ] .电力科学与技术学报，2024，39（1）：28-46.

郭晨阳，高辉，李炜卓，等. 新型电力系统下分层分区平衡架构研究综述 [J ] .分布式能源，2026，11（1）：1-10.

赵倩宇，王璐洋，王守相. 新型配电系统灵活性及其评价指标综述 [J ] .供用电，2024，41（8）：35-44.

LIU Y，NING P，REITER M K. False data injection attacks against state estimation in electric power grids [J ] .ACM Transactions on Information and System Security （TISSEC），2011，14（1）：1-33.

郭晓利，王月，李斌. 基于关联差异的电力信息物理系统虚假数据注入攻击检测 [J ] .电力系统保护与控制，2025，53（21）：166-177.

刘永慧，卢艳杰. 网络攻击下直流微电网系统的事件触发滑模控制 [J ] .电力科学与技术学报，2024，39（6）：212-221.

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.

LI X，WANG Z，ZHANG C，et al. A novel dynamic watermarking-based EKF detection method for FDIAs in smart grid [J ] .IEEE/CAA Journal of Automatica Sinica，2022，9（7）：1319-1322.

GOU L，SUN R，HAN X. FDIA system for sensors of the aero-engine control system based on the immune fusion kalman filter [J ] . Mathematical Problems in Engineering，2021（1）：1-17.

夏卓群，曾悠优，尹波，等. 电力网络中基于物理信息的虚假数据入侵检测方法 [J ] . 信息网络安全，2019，（4）：29-36.

杨杉，谭博，郭静波. 基于双马尔科夫链的新型能源互联网虚假数据注入攻击检测 [J ] . 电力自动化设备，2021，41（2）：131-137.

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.

CHAKRABARTY S，SIKDAR B. Detection of malicious command injection attacks on phase shifter control in power systems [J ] .IEEE Transactions on Power Systems，2020，36（1）：271-280.

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.

周先军，王茹，刘航，等. 基于CNN-CBAM的虚假数据注入攻击辨识研究 [J ] . 光通信研究，2024，（3）：49-55.

WANG S，BI S，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.

JIANG W，LAN K，LI Y，et al. A dual-channel CNN for precise localization of false data injection attacks in smart grids [J ] .Iranian Journal of Science and Technology，Transactions of Electrical Engineering，2025，49 （4）：1693-1710.

SHEN K，YAN W，NI H，et al. Localization of false data injection attack in smart grids based on SSA-CNN [J ] . Information，2023，14（3）：180.

IBRAHEEM R，EDDIN M E，MASSAOUDI M，et al. Enhancing locational FDIA detection in smart grids：a hyperparameter optimization analysis [C ] //2024 4th International Conference on Smart Grid and Renewable Energy （SGRE）. Doha，Qatar，2024：1-6.

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.

WANG D，GAO B，ZHANG L. Optimization on electric construction machinery considering time‐of‐use electricity price based on the improved crested porcupine optimizer algorithm [J ] . Energy Science & Engineering，2025，13（6）：2973-2986.

HU J，SHEN L，SUN G. Squeeze-and-excitation networks [C ] //Proceedings of the IEEE conference on computer vision and pattern recognition.Salt Lake City，USA，2018：7132-7141.

杨玉泽，刘文霞，刘耕铭，等. 不完全信息下计及残差污染的虚假数据注入攻击新模式 [J ] .中国电机工程学报，2025，45（19）：7481-7493.

席磊，王艺晓，熊雅慧，等. 基于改进深度极限学习机的电网虚假数据注入攻击定位检测 [J ] .发电技术，2025，46（3）：521-531.

YAO X，LIU Y，LIN G. Evolutionary programming made faster [J ] .IEEE Transactions on Evolutionary computation，1999，3（2）：82-102.

SONI P，MISHRA P，MONDAL D. A novel amalgamation of pre-processing technique and CNN model for accurate classification of power quality disturbances [J ] .Electrical Engineering，2025，107（4）：5187-5206.

高芷蓉，杨杉，喻希，等. 基于CNN-BiLSTM-Attention的电力系统虚假数据注入攻击检测 [J ] .智慧电力，2025，53（4）：103-111.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Traveling Wave Time-Frequency Spectrogram and Improved CNN Based Method for Ground Fault Location in Substation DC Systems

Multi-time Scale Adequacy Assessment and Quantitative Analysis of New-type Electric Power Systems

Transmission Line Fault Classification Based on Deep Learning and Imbalanced Sample Set

Power Quality Disturbance Recognition Method Based on Multi-layer Feature Fusion Attention Network

Non-invasive Load Monitoring Method Based on Novel Convolutional Neural Network

Related Author

LI Baopeng

WANG Hongyang

SHAO Kexin

LIU Yongjun

HAI Zhichen

XING Haijun

SUN Yiwen

SHI Yiqin

Related Institution

College of Automation and Electrical Engineering，Lanzhou Jiaotong University

State Grid Dengzhou Power Supply Company，Dengzhou

College of Electrical Engineering，Shanghai University of Electric Power

（School of Automation， Guangdong University of Technology，，）

School of Electrical Engineering， Guangxi University

AI问答

⁰