Traffic Latency Characterization and Fingerprinting in Mobile Cellular Networks
-
摘要: Internet骨干网流量中，混合了来自于固网接入和3G/4G移动蜂窝网络接入的不同客户端流量.在不依赖于应用层信息和查看数据报内容的前提下，使用传统的流量分析方法和特征选择，难以将两者正确区分.通过对移动蜂窝网络通信链路技术和无线资源控制(radio resource control， RRC)机制导致IP数据报时延波动的分析建模，结合TCP/IP协议数据报的往返时延(round-trip time， RTT)计算，构建了6个与数据报时延相关的网络流量特征，用于有效区分通过3G/4G和固网接入的网络流量来源.这些特征能够针对不同网络节点接入互联网技术差异所带来的网络数据包时序分布特点进行描述和匹配.在此基础上，采用多种有监督的机器学习方法，搭建了基于网络流量的分类模型并进行交叉验证.实验结果表明：利用这些时延特征建立的流量描述与分类模型，能够有效区分移动蜂窝网络接入数据流量和固网接入数据流量，分类正确率达到92%以上，并具有良好的覆盖性与容错性.Abstract: Internet backbone traffic is a complicated mix of various data flows initiated by clients via different network connections, including 3G/4G-based mobile cellular networks and wired broadband networks. Without examining application layer meta-data or inspecting into TCP/IP packet contents, existing network traffic analysis and characterization methods struggle in differentiating traffic flows from these two types of network connections. By studying the different kinds of link layer technics and wireless radio resource control (RRC) mechanisms, the traffic temporal characteristics are analyzed and formalized based on the packet delay variance. By making use of TCP/IP packet’s round-trip time (RTT) calculation, the experiments extract six significant network traffic features related to the packet delay, and apply them to train and test machine-learning classifiers to separate 3G/4G client traffic flows from broadband connection flows. These features focus on the transmission latency caused by a client’s first-hop Internet connection, and reveal the temporal variance of packet distribution from different link flows. Experiments with realistic dataset of mobile application traffic achieve a classification precision of more than 92% with effective traffic coverage and error resilience. The proposed method surpasses other related solutions also by relying on only the temporal distribution of flow packets without needing to inspect the packet content and encapsulation.
-
Keywords:
- 3G/4G /
- mobile cellular network /
- traffic characterization /
- RRC mechanism /
- network delay
-
-
期刊类型引用(11)
1. 林晓庆. 基于物联网的电力计量主站采集链路监测研究. 信息技术. 2024(03): 104-109+115 . 
百度学术
2. 贾万祥，张平华. 基于多特征识别的非线性网络流量异常检测方法. 湖北科技学院学报. 2023(02): 145-150 . 百度学术
3. 王于琴，田峰. 基于动态神经网络的时延自动化控制数学建模研究. 自动化与仪器仪表. 2022(05): 79-83 . 百度学术
4. 张旭，李鹏. 基于改进CUSUM算法的移动恶意软件TD算法. 计算机仿真. 2022(06): 365-368+390 . 百度学术
5. 王峰，于青民，黄颖，段世惠. 工业互联网网络关键技术与发展研究. 电信科学. 2022(07): 106-113 . 百度学术
6. 俞永飞. 基于人工蜂群算法的网络攻击流量自动辨识研究. 内蒙古民族大学学报(自然科学版). 2022(04): 277-283 . 百度学术
7. 佘静，胡睿. 基于信号时变性的空间光通信网络优化研究. 激光杂志. 2022(09): 129-133 . 百度学术
8. 杨峰，马铭. 基于负载随机性的互联网络链路流量识别方法. 计算机仿真. 2021(11): 331-334+339 . 百度学术
9. 张宇，刘珊. 蚁群算法优化极限学习机的通信网络流量建模分析. 甘肃科学学报. 2021(06): 29-33 . 百度学术
10. 陆威，方琰崴，陈亚权. URLLC超低时延解决方案和关键技术. 移动通信. 2020(02): 8-14 . 百度学术
11. 董晓庆，程良伦，郑耿忠，王涛. 认知异构无线网络中传输速率最大化的频谱资源分配方法. 通信学报. 2019(09): 124-135 . 百度学术
其他类型引用(3)
计量
- 文章访问数: 949
- HTML全文浏览量: 1
- PDF下载量: 421
- 被引次数: 14
下载:
