基于扩散模型的电网数字化系统背景流量生成

孙璇; 乔梦妍; 李军; 申立艳; 代海英; 郝楠; 常启诚; 周昊

doi:10.11930/j.issn.1004-9649.202507021

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

基于扩散模型的电网数字化系统背景流量生成

能源电力数据要素与人工智能应用 | 更新时间：2026-02-03

- 基于扩散模型的电网数字化系统背景流量生成
- Diffusion model-based background traffic generation for power grid digital systems
- 中国电力 2026年59卷第1期页码：66-75
- 作者机构：
  
  1. 北京信息科技大学计算机学院,北京,102206
  2. 国网新源控股有限公司检修分公司,北京,100053
  3. 美国联邦住房贷款抵押公司，美国弗吉尼亚州,22102
  4. 国家工业信息安全发展研究中心工业信息安全感知与评估技术工业和信息化部重点实验室,北京,100040
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目（62302057）;国网新源集团有限公司科技项目（SGXYKJ-2025-033）。
- DOI：10.11930/j.issn.1004-9649.202507021
  中图分类号：
- 网络出版：2026-01-13，
  
  纸质出版：2026-01-13
- 稿件说明：
移动端阅览
孙璇, 乔梦妍, 李军, 申立艳, 代海英, 郝楠, 常启诚, 周昊. 基于扩散模型的电网数字化系统背景流量生成[J]. 中国电力, 2026, 59(1): 66-75.

孙璇, 乔梦妍, 李军, et al. Diffusion model-based background traffic generation for power grid digital systems[J]. 2026, 59(1): 66-75.
孙璇, 乔梦妍, 李军, 申立艳, 代海英, 郝楠, 常启诚, 周昊. 基于扩散模型的电网数字化系统背景流量生成[J]. 中国电力, 2026, 59(1): 66-75. DOI： 10.11930/j.issn.1004-9649.202507021.

孙璇, 乔梦妍, 李军, et al. Diffusion model-based background traffic generation for power grid digital systems[J]. 2026, 59(1): 66-75. DOI： 10.11930/j.issn.1004-9649.202507021.

摘要

为解决当前电网通信背景流量生成方法在协议行为建模、时序依赖捕捉及流量类别控制等方面存在的不足，提出一种基于扩散模型和双向流特征（diffusion models and bidirectional flow，DMBF）的背景流量生成方法。通过改进的流量图像化表示（transforming basic flow data into an intuitive picture，FlowPic）机制提取具有方向性、时间性与包长耦合特征的双向会话图像，结合Transformer实现时序建模；引入条件控制机制为不同类别的流量设定生成比例；通过扩散模型生成背景流量。为验证方法的实用性与通用性，在包含公开流量和来源于实际网络环境的通信数据上进行实验，覆盖多个典型业务场景与交互模式。结果表明，DMBF在生成精度与分布一致性上优于传统生成对抗网络方法，JSD降至28.89%，MAE和RMSE分别为26.24%、30.91%。

Abstract

To address the limitations of current background traffic generation methods in power communication—particularly in modeling protocol behaviors

capturing temporal dependencies

and controlling traffic category distributions—this paper proposes a background traffic generation approach based on diffusion models and bidirectional flow (DMBF). By employing transforms basic flow data into an intuitive picture (FlowPic)

we extract bidirectional session images featuring directionality

temporality

and packet-length coupling characteristics. This is combined with a Transformer for temporal modeling. A conditional control mechanism is introduced to adjust the generation ratios of different traffic types

enabling the diffusion model to generate background flows under guided conditions. To evaluate the practicality and generalizability of the proposed method

experiments are conducted on datasets comprising both publicly available traffic samples and real-world network communication data

covering a range of typical business scenarios and interaction patterns. Experimental results show that DMBF outperforms traditional generative adversarial network approaches in terms of generation accuracy and distributional consistency. JSD decreased to 28.89%

with MAE and RMSE at 26.24% and 30.91%

respectively.

关键词

Keywords

references

1吴辉, 邹子威, 肖丰明, 等. 基于BiLSTM与自注意力机制生成对抗网络的GSA防护方法[J]. 中国电力, 2024, 57 (9): 61- 70.

WU Hui, ZOU Ziwei, XIAO Fengming, et al. Defense method for smart grid GPS spoofing attack based on BiLSTM and self-attention mechanism generative adversarial network[J]. Electric Power, 2024, 57 (9): 61- 70.

2余江, 高宏慧, 史泽兵, 等. 继电保护远程运维系统报文合规检测及入侵阻断技术应用[J]. 中国电力, 2024, 57 (3): 135- 143, 151.

YU Jiang, GAO Honghui, SHI Zebing, et al. Application of message compliance detection and intrusion blocking technology in remote operation and maintenance system of relay protection[J]. Electric Power, 2024, 57 (3): 135- 143, 151.

3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.

TAO Lei, LUO Pingping, LIN Jikeng. Two-stage detection method for DC microgrid false data injection attack based on deep learning[J]. Electric Power, 2024, 57 (9): 11- 19.

4闫正义, 赵康, 王凯. 基于强化学习的新型电力系统优化策略应用综述[J]. 发电技术, 2025, 46 (3): 508- 520.

YAN Zhengyi, ZHAO Kang, WANG Kai. Review of application on optimization strategies for new-type power system based on reinforcement learning[J]. Power Generation Technology, 2025, 46 (3): 508- 520.

5岳芳, 王雪珍, 姜山. 智能电网的网络安全风险及应对策略[J]. 科技导报, 2024, 42 (9): 6- 16.

YUE Fang, WANG Xuezhen, JIANG Shan. Network security risks and new countermeasures under the smart grid environment[J]. Science & Technology Review, 2024, 42 (9): 6- 16.

6ACHAAL B, ADDA M, BERGER M, et al. Study of smart grid cyber-security, examining architectures, communication networks, cyber-attacks, countermeasure techniques, and challenges[J]. Cybersecurity, 2024, 7 (1): 10.

7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.

XI Lei, WANG Yixiao, XIONG Yahui, et al. Location detection of false data injection attacks in power grid based on improved deep extreme learning machine[J]. Power Generation Technology, 2025, 46 (3): 521- 531.

8刘刚, 田志浩, 黄颖峰, 等. 考虑虚拟电厂的电力系统一致性经济调度方法[J]. 中国电力, 2025, 58 (6): 105- 111.

LIU Gang, TIAN Zhihao, HUANG Yingfeng, et al. Consistency economic dispatch method for power systems considering virtual power plants[J]. Electric Power, 2025, 58 (6): 105- 111.

9周劼英, 张晓, 邵立嵩, 等. 新型电力系统网络安全防护挑战与展望[J]. 电力系统自动化, 2023, 47 (8): 15- 24.

ZHOU Jieying, ZHANG Xiao, SHAO Lisong, et al. Challenges and prospects of cyber security protection for new power system[J]. Automation of Electric Power Systems, 2023, 47 (8): 15- 24.

10周洋, 黄德志, 李培栋, 等. 考虑平衡端点相位不对称及光伏接入的低压配电网三相潮流模型[J]. 中国电力, 2024, 57 (10): 190- 198.

ZHOU Yang, HUANG Dezhi, LI Peidong, et al. A three-phase power flow model for low-voltage distribution networks considering balanced bus phase asymmetry and photovoltaic access[J]. Electric Power, 2024, 57 (10): 190- 198.

11XIE Y J, ZHANG Y C, LEE W J, et al. Virtual power plants for grid resilience: a concise overview of research and applications[J]. IEEE/CAA Journal of Automatica Sinica, 2024, 11 (2): 329- 343.

12杨珂, 王栋, 李达, 等. 虚拟电厂网络安全风险评估指标体系构建及量化计算[J]. 中国电力, 2024, 57 (8): 130- 137.

YANG Ke, WANG Dong, LI Da, et al. Network security risk assessment index system and calculation for virtual power plant[J]. Electric Power, 2024, 57 (8): 130- 137.

14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. Application of machine learning in cyber security of cyber-physical power system[J]. Automation of Electric Power Systems, 2022, 46 (9): 200- 215.

15姜力杨, 盖晨昊, 齐航, 等. 数据驱动的电力系统动态安全评估研究综述[J]. 山东电力技术, 2024, 51 (4): 27- 35.

JIANG Liyang, GAI Chenhao, QI Hang, et al. Review on data-driven dynamic security assessment of power systems[J]. Shandong Electric Power, 2024, 51 (4): 27- 35.

16田鑫, 靳晓凌, 韩新阳, 等. 基于机器学习算法的新型电力系统中电网投资成效评价及投资推演[J]. 中国电力, 2025, 58 (7): 197- 206.

TIAN Xin, JIN Xiaoling, HAN Xinyang, et al. Evaluation of grid investment effectiveness and investment simulation for new-type power systems based on machine learning algorithm[J]. Electric Power, 2025, 58 (7): 197- 206.

17陈艺璇, 王嘉阳, 卓映君, 等. 人工智能在电力系统运行模拟加速中的应用综述[J]. 发电技术, 2025, 46 (3): 467- 481.

CHEN Yixuan, WANG Jiayang, ZHUO Yingjun, et al. Review of artificial intelligence applications in accelerating operational simulation of power systems[J]. Power Generation Technology, 2025, 46 (3): 467- 481.

18YAN Q, WANG M D, HUANG W Y, et al. Automatically synthesizing DoS attack traces using generative adversarial networks[J]. International Journal of Machine Learning and Cybernetics, 2019, 10 (12): 3387- 3396.

19司雅昕, 刘训强, 苏向敬, 等. 海上风电功率预测研究综述[J]. 浙江电力, 2025, 44 (11): 59- 71.

SI Yaxin, LIU Xunqiang, SU Xiangjing, et al. A review of offshore wind power forecasting studies[J]. Zhejiang Electric Power, 2025, 44 (11): 59- 71.

20胡永进, 郭渊博, 马骏, 等. 基于对抗样本的网络欺骗流量生成方法[J]. 通信学报, 2020, 41 (9): 59- 70.

HU Yongjin, GUO Yuanbo, MA Jun, et al. Method to generate cyber deception traffic based on adversarial sample[J]. Journal on Communications, 2020, 41 (9): 59- 70.

21DU L F, HE J J, LI T, et al. DBWE-Corbat: Background network traffic generation using dynamic word embedding and contrastive learning for cyber range[J]. Computers & Security, 2023, 129, 103202.

22薛明军, 徐胜, 邹磊, 等. 考虑通信流量控制的配电网线路5G差动保护方案[J]. 浙江电力, 2024, 43 (7): 29- 36.

XUE Mingjun, XU Sheng, ZOU Lei, et al. A 5G-enabled scheme for differential protection of distribution lines considering data flow control[J]. Zhejiang Electric Power, 2024, 43 (7): 29- 36.

24康未, 李维皓, 刘桐菊. 基于生成对抗神经网络的流量生成方法研究[J]. 网络安全与数据治理, 2024, 43 (6): 33- 41.

KANG Wei, LI Weihao, LIU Tongju. Traffic generation methods based on generative adversarial neural networks[J]. Cyber Security and Data Governance, 2024, 43 (6): 33- 41.

25SHAPIRA T, SHAVITT Y. FlowPic: a generic representation for encrypted traffic classification and applications identification[J]. IEEE Transactions on Network and Service Management, 2021, 18 (2): 1218- 1232.

26LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86 (11): 2278- 2324.

27CHAI H Y, JIANG T, YU L. Diffusion model-based mobile traffic generation with open data for network planning and optimization[C]//Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Barcelona Spain. ACM, 2024: 4828–4838.

28DRAPER-GIL G, LASHKARI A H, MAMUN M S I, et al. Characterization of encrypted and VPN traffic using time-related features[C]//Proceedings of the 2nd International Conference on Information Systems Security and Privacy. Rome, Italy. SCITEPRESS-Science and and Technology Publications, 2016: 407–414.

29MAO X D, LI Q, XIE H R, et al. Least squares generative adversarial networks[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy. IEEE, 2017: 2813–2821.

31陈志永, 韩璟琳, 刘洋, 等. 基于关键帧提取与图像识别的电网设施数字化重建[J]. 中国电力, 2024, 57 (9): 217- 223.

CHEN Zhiyong, HAN Jinglin, LIU Yang, et al. 3D reconstruction of power grid facilities based on keyframe extraction and image recognition[J]. Electric Power, 2024, 57 (9): 217- 223.

32YANG B, LIU S W, GAO H D. Energy e-commerce user portrait and multi-agent cooperative game price mechanism design[J]. Frontiers in Energy Research, 2024, 12, 1379612.

33钟成, 翟迪, 陆阳, 等. 城市电网本地通信网络数字化感知业务与通信技术适配研究[J]. 中国电力, 2023, 56 (8): 86- 98.

ZHONG Cheng, ZHAI Di, LU Yang, et al. Adaptation of digital perception service and communication technologies for local communication network of urban grid[J]. Electric Power, 2023, 56 (8): 86- 98.

34张兰. 电网企业标准数字化发展现状及趋势分析[J]. 湖南电力, 2023, 43 (1): 95- 98, 102.

ZHANG Lan. Development status and trend analysis of standard digitization in power grid enterprise[J]. Hunan Electric Power, 2023, 43 (1): 95- 98, 102.

35戎毅成, 谭鑫, 高瑾, 等. 基于物联网的电网施工智慧工地数字化管理平台建设[J]. 山东电力技术, 2023, 50 (4): 22- 27.

RONG Yicheng, TAN Xin, GAO Jin, et al. Construction of digital management platform for power grid intelligent construction site based on Internet of Things[J]. Shandong Electric Power, 2023, 50 (4): 22- 27.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于双层注意力机制的电力文本分类模型

基于MSCNN-BiGRU-Attention的短期电力负荷预测

基于改进生成对抗网络的风光气象资源联合场景生成方法

面向稳控系统E1通道的网络靶场实验台的设计与实现

中国光学1-6期(第5卷)2012年(双月刊)总目次