基于GAN和XGBoost融合的高精度业务流量识别方法

关其峰; 赵夙; 朱晓荣

doi:10.13756/j.gtxyj.2023.03.004

您当前的位置：

首页 >

文章列表页 >

基于GAN和XGBoost融合的高精度业务流量识别方法

光通信系统与网络技术 | 更新时间：2023-05-25

- 基于GAN和XGBoost融合的高精度业务流量识别方法
- High Precision Traffic Identification Method based on GAN and XGBoost Fusion
- 光通信研究 2023年第3期页码：19-23
- 作者机构：
  
  南京邮电大学江苏省无线通信重点实验室，南京　210003
- 作者简介：
  
  关其峰，硕士。E-mail：841822982@qq.com
- 基金信息：
  
  国家自然科学基金资助项目(61871237;92067101);江苏省重点研发计划资助项目(BE2021013-3)
- DOI：10.13756/j.gtxyj.2023.03.004
  中图分类号： TN915
- 纸质出版日期：2023-06-10，
  
  收稿日期：2022-07-28，
  
  修回日期：2022-08-24，
扫描看全文
关其峰，赵夙，朱晓荣.基于GAN和XGBoost融合的高精度业务流量识别方法[J].光通信研究，2023(3):19-23.

Guan Q F, Zhao S, Zhu X R. High Precision Traffic Identification Method based on GAN and XGBoost Fusion[J]. Study on Optical Communications, 2023(3):19-23.
关其峰，赵夙，朱晓荣.基于GAN和XGBoost融合的高精度业务流量识别方法[J].光通信研究，2023(3):19-23. DOI： 10.13756/j.gtxyj.2023.03.004.

Guan Q F, Zhao S, Zhu X R. High Precision Traffic Identification Method based on GAN and XGBoost Fusion[J]. Study on Optical Communications, 2023(3):19-23. DOI： 10.13756/j.gtxyj.2023.03.004.

摘要

随着互联网技术的不断发展以及网络规模的不断扩大，新的网络业务层出不穷，为了保障用户服务质量，准确快速地对业务流量进行分类是目前的研究重点。传统业务识别方法多以协议或具体业务为分类依据，应用性较低。文章结合业务流量特征和机器学习方法，提出了一种基于生成对抗网络（GAN）和极端梯度增强（XGBoost）融合的业务流量识别方法。该方法首先提取代表业务资源需求的流量特征；然后通过改进GAN算法扩充少数类样本，解决业务识别过程中出现的数据集分布不平衡导致的模型准确率低的问题；最后通过随机森林算法进行特征选择，并利用XGBoost算法完成模型训练。结果表明，该方法对业务识别的准确率达到了97.32%。

Abstract

With the continuous development of Internet technology and the continuous expansion of network scale

new network services emerge in an endless stream. In order to ensure the quality of user service

accurate and rapid classification of application traffic is the focus of current research. The traditional service identification method is based on protocol or specific service classification

which is suffered from low applicability. Combining traffic characteristics and machine learning methods

this paper proposes a traffic identification method based on the fusion of Generative Adversative Network (GAN) and Extreme Gradient Lift Boosting (XGBoost). Firstly

the traffic characteristics representing service resource requirements. Then GAN algorithm was improved to expand a few class samples to solve the problem of low model accuracy caused by the unbalanced distribution of data sets in the process of application identification. Finally

the random forest algorithm was used to select the feature

and the XGBoost algorithm was used to complete the model training. The results show that the accuracy of this method is 97.32%.

关键词

业务识别极端梯度增强生成对抗网络不平衡数据特征降维

Keywords

application identificationXGBoostGANunbalanced datafeature reduction

references

Dainotti A, Pescape A, Claffy K C. Issues and Future Directions in Traffic Classification[J]. Network IEEE, 2012, 26(1):35-40.

Moore A W, Papagiannaki K. Toward the Accurate Identification of Network Applications[C]//2005 6th International Workshop. Boston, MA, USA:PAM, 2005:41-54.

Lin P C, Lin Y D, Lee T H, et al. Using String Matching for Deep Packet Inspection[J]. Computer, 2008, 41(4):23-28.

Dubin R, Dvir A, Pele O, et al. I Know What You Saw Last Minute-encrypted HTTP Adaptive Video Streaming Title Classification[J]. IEEE Transactions on Information Forensics and Security, 2017, 12(12):3039-3049.

Liu C C, Chang Y, Tseng C W, et al. SVM-based Classification Mechanism and Its Application in SDN Networks[C]//2018 10th International Conference on Communication Software and Networks (ICCSN). Chengdu, China:IEEE, 2018:45-49.

Zhai Y, Zheng X. Random Forest based Traffic Classification Method in SDN [C]//2018 International Conference on Cloud Computing, Big Data and Blockchain (ICCBB). Fuzhou, China:IEEE, 2018: 1-5.

Moreira R, Rodrigues L F, Rosa P F, et al. Packet Vision: a Convolutional Neural Network Npproach for Network Traffic Classification [C]//2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). Porto de Galinhas, Brazil:IEEE, 2020:256-263.

Lotfollahi M, Siavoshani M J, Zade R S H. Deep Packet: a Novel Approach for Encrypted Traffic Classification Using Deep Learning[J]. Soft Computing, 2019, 24:1999-2012.

靳瑞哲, 迟楠. 基于机器学习的调制格式识别算法研究[J]. 光通信研究, 2022(6):9-15.

Jin R Z, Chi N. Research on Modulation Format Recognition Algorithm based on Machine Learning[J]. Study on Optical Communications, 2022(6):9-15.

Rekha G, Tyagi A K, Sreenath N, et al. Class Imbalanced Data: Open Issues and Future Research Directions [C]//2021 International Conference on Computer Communication and Informatics (ICCCI). Coimbatore, India:IEEE, 2021:1-6.

Wang Z X, Wang P, Zhou X, et al. FLOWGAN:Unbalanced Network Encrypted Traffic Identification Method based on GAN [C]//2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking. Xiamen, China:IEEE, 2019:975-983.

王正龙, 张保稳.生成对抗网络研究综述[J]. 网络与信息安全学报, 2021, 7(4):68-85.

Wang Z L, Zhang B W. A Survey of Generative Adversarial Networks[J]. Journal of Network and Information Security, 2021, 7(4):68-85.

Gulrajani I, Ahmed F, Arjovsky M, et al. Improved Training of Wasserstein GANs[C]//In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17). Red Hook, NY, USA: Curran Associates Inc, 2017: 5769-5779.

Peng X, Li J, Wang G, et al. Random Forest based Optimal Feature Selection for Partial Discharge Pattern Recognition in HV Cables[J]. IEEE Transactions on Power Delivery, 2019, 34(4):1715-1724.

更多指标>

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

暂无数据