一种基于深度学习的轻量化流量识别模型  

A Lightweight Traffic Identification Model Based on Deep Learning

作　　者：李勇 任勇毛[1,2] 殷卓然 周旭 LI Yong;REN Yongmao;YIN Zhuoran;ZHOU Xu(Computer Network Information Center,Chinese Academy of Sciences,Beijing 100083,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院计算机网络信息中心,北京100083 [2]中国科学院大学,北京100049

出　　处：《数据与计算发展前沿(中英文)》2025年第2期3-11,共9页Frontiers of Data & Computing

基　　金：中国科学院湖南省联合攻关项目(2024JK4001);北京市自然科学基金项目(1232011)。

摘　　要：【目的】针对深度学习流量识别模型通常面临较高的参数量和计算量,难以在资源受限的边缘网络环境中部署,提出了一种基于ShuffleNetV2改进的轻量化流量识别模型。【方法】首先,选择合适的模型分辨率因子和宽度因子来平衡模型的效率和性能;其次,在模型中嵌入轻量级多尺度特征融合模块和改进的坐标注意力机制模块,旨在以较小的计算存储开销提升模型的识别性能;最后,将模型中的激活函数ReLU替换成ReLU6,更有利于模型在资源受限的环境中部署与推理。【结果】实验基于公开的ISCXVPN2016数据集,结果验证了该模型在识别精度和执行效率上的良好表现。与现有广泛采用的ResNet-18模型相比,该模型在准确率(98.8%)增加0.2%的情况下,参数量和计算量分别大幅下降96.46%和62.97%。【结论】模型在保持较高的准确率的同时,显著实现了轻量化。[Objective]To address the issue of deep learning-based traffic identification models typically having high parameter count and computational complexity,which limits their deployment in resource-constrained edge networks,a lightweight traffic identification model based on an improved ShuffleNetV2 is proposed.[Methods]First,appropriate resolution and width factors are selected to balance the model’s efficiency and performance.Second,a lightweight multiscale feature fusion module and an enhanced coordinate attention mechanism module are integrated into the model to improve identification performance with minimal computational and storage overhead.Finally,the ReLU activation function is replaced with ReLU6 to enhance the model’s suitability for deployment and inference in resource-limited settings.[Results]The experiments are conducted based on the publicly available ISCXVPN2016 dataset,and the results validate the model's excellent performance in terms of recognition accuracy and execution efficiency.Compared to the widely adopted ResNet-18 model,this model achieves an accuracy increase of 0.2%(reaching 98.8%),while significantly reducing the parameter count and computational complexity by 96.46%and 62.97%,respectively.[Conclusions]The model achieves significant lightweighting while maintaining high accuracy.

关 键 词：流量识别 ShuffleNetV2 注意力机制 特征融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP391.4[自动化与计算机技术—计算机科学与技术]