A Timeliness-Enhanced Traffic Identification Method in Airborne Network

一种时效增强的机载网络流量识别方法

¹ School of Information and Navigation, Air Force Engineering University, Xi'an 710077, China
² PLA 31006 Troops, Beijing 100000, China
³ School of Cybersecurity, Northwestern Polytechnical University, Xi'an 710072, China

Received: 21 June 2019

Abstract

High dynamic topology and limited bandwidth of the airborne network make it difficult to provide reliable information interaction services for diverse combat mission of aviation swarm operations. Therefore, it is necessary to identify the elephant flows in the network in real time to optimize the process of traffic control and improve the performance of airborne network. Aiming at this problem, a timeliness-enhanced traffic identification method based on machine learning Bayesian network model is proposed. Firstly, the data flow training subset is obtained by preprocessing the original traffic dataset, and the sub-classifier is constructed based on Bayesian network model. Then, the multi-window dynamic Bayesian network classifier model is designed to enable the early identification of elephant flow. The simulation results show that compared with the existing elephant flow identification method, the proposed method can effectively improve the timeliness of identification under the condition of ensuring the accuracy of identification.

摘要

机载网络拓扑动态性强，带宽受限等特点导致其难以为多样化的航空集群作战任务提供可靠的信息交互服务，因此需要对网络中的"大流量对象"进行实时识别，从而优化流量控制，提升网络性能。针对该问题，基于机器学习贝叶斯模型，提出一种时效增强的流量识别方法，首先通过对原始流量数据集进行预处理得到数据流训练子集，并基于贝叶斯网络模型构造子分类器，然后基于多窗口动态贝叶斯网络分类器模型实现大流量对象的早期识别。仿真结果表明，相较于现有的大流识别方法，所提方法可以在保证识别准确性的条件下有效提升识别时效性。