Study On Optical Communications, Volume. 49, Issue 3, 19(2023)

High Precision Traffic Identification Method based on GAN and XGBoost Fusion

Qi-feng GUAN*... Su ZHAO and Xiao-rong ZHU |Show fewer author(s)
Author Affiliations
  • Jiangsu Key Laboratory of Wireless Communication, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • show less

    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%.

    Tools

    Get Citation

    Copy Citation Text

    Qi-feng GUAN, Su ZHAO, Xiao-rong ZHU. High Precision Traffic Identification Method based on GAN and XGBoost Fusion[J]. Study On Optical Communications, 2023, 49(3): 19

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Research Articles

    Received: Jul. 28, 2022

    Accepted: --

    Published Online: Jun. 12, 2023

    The Author Email: GUAN Qi-feng (841822982@qq.com)

    DOI:10.13756/j.gtxyj.2023.03.004

    Topics