发电技术 ›› 2026, Vol. 47 ›› Issue (2): 345-358.DOI: 10.12096/j.2096-4528.pgt.260212

• 新型电力系统 • 上一篇    

抵抗虚假数据注入攻击的综合能源系统弹性提升策略

吴丽珍1, 张永朋1, 魏建平1,2, 陈伟1,3   

  1. 1.兰州理工大学电气工程与信息工程学院,甘肃省 兰州市 730050
    2.北京交通大学国家能源主动配电网技术研发中心,北京市 海淀区 100044
    3.兰州理工大学国家级电气与控制工程实验教学中心,甘肃省 兰州市 730050
  • 收稿日期:2025-01-23 修回日期:2025-03-30 出版日期:2026-04-30 发布日期:2026-04-21
  • 作者简介:吴丽珍(1973),女,博士,教授,研究方向为分布式发电技术、微电网与微能源网的稳定运行与控制,wulzlut@163.com
    张永朋(1997),男,硕士研究生,研究方向为电力系统信息网络安全和综合能源系统优化调度, 2432696815@qq.com
    魏建平(1998),男,硕士研究生,研究方向为分布式发电与微网协调控制,18893728728@163.com
    陈伟(1976),男,博士,教授,研究方向为智能电网的电能质量分析与控制,1341814827@qq.com
  • 基金资助:
    国家自然科学基金项目(62063016)

Resilience Enhancement Strategies for Integrated Energy Systems Against False Data Injection Attacks

Lizhen WU1, Yongpeng ZHANG1, Jianping WEI1,2, Wei CHEN1,3   

  1. 1.College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, Gansu Province, China
    2.National Active Distribution Network Technology Research Center, Beijing Jiaotong University, Haidian District, Beijing 100044, China
    3.National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou 730050, Gansu Province, China
  • Received:2025-01-23 Revised:2025-03-30 Published:2026-04-30 Online:2026-04-21
  • Supported by:
    National Natural Science Foundation of China(62063016)

摘要:

目的 网络的开放性导致综合能源系统易受网络攻击,研究综合能源系统(integrated energy system,IES)遭受虚假数据注入攻击(false data injection attack,FDIA)后的弹性提升问题。 方法 构造系统遭受到FDIA后的弹性提升框架,建立考虑安全性及经济性的系统弹性评估方法。在分析能量流与信息流攻击机理的基础上,提出基于连续小波变换(continuous wavelet transform,CWT)和卷积神经网络(convolutional neural network,CNN)的能量流FDIA检测方法,以及基于CWT和广义回归神经网络模型(general regression neural network,GRNN)的信息流FDIA检测方法。进一步分析FDIA对系统调度造成的影响,建立优化调度模型,提升系统受到网络攻击后的弹性。 结果 含CWT+GRNN检测模型的综合能源系统弹性提升策略比不含检测模型的提升策略更具优越性,安全可靠性高出22.79%,运行经济性高出12.89%,弹性提升水平高出19.82%。含检测模型的综合能源系统弹性提升策略接近于不受网络攻击运行时的水平。 结论 基于CWT+GRNN检测模型的综合能源系统弹性提升策略在系统受FDIA后能够明显提升系统弹性,使系统性能接近于正常运行时的水平。

关键词: 电-热-气, 综合能源系统(IES), 虚假数据注入攻击(FDIA), 攻击检测, 优化调度, 弹性提升

Abstract:

Objectives The openness of the network makes integrated energy systems vulnerable to cyber attacks, focusing on the resilience enhancement of integrated energy systems (IES) against false data injection attacks (FDIA). Methods A resilience enhancement framework is developed for IES under FDIA, and a system resilience assessment method is established, with the inclusion of both security and economic factors. Based on the analysis of energy flow and information flow attack mechanisms, an FDIA detection method for energy flow is proposed using continuous wavelet transform (CWT) and convolutional neural network (CNN). Additionally, an FDIA detection method for information flow is developed using CWT and general regression neural network (GRNN) model. The effect of FDIA on system scheduling is further analyzed, and an optimized scheduling model is established to enhance system resilience after experiencing cyberattacks. Results Compared with strategies without detection models, the resilience enhancement strategy incorporating CWT+GRNN detection models demonstrates better performance, with a 22.79% improvement in security and reliability, a 12.89% increase in operational economy, and a 19.82% higher resilience level. The resilience enhancement strategy incorporating detection models achieves performance levels close to those of normal operation without cyberattacks. Conclusions The proposed resilience enhancement strategy for IES based on CWT+GRNN detection model significantly improves system resilience after FDIA, bringing the system performance close to its normal operation level.

Key words: electricity-heat-gas, integrated energy system(IES), false data injection attack(FDIA), attack detection, optimized scheduling, resilience enhancement

中图分类号: