Flow-Packet Hybrid Traffic Classification for Class-Aware Network Routing
This addresses practical limitations in deploying machine learning for real-time traffic classification in network routing, though it is incremental by building on existing flow-based and packet-based approaches.
The paper tackles the problem of network traffic classification at routers by introducing a flow-packet hybrid method that avoids waiting for flow completion and reduces computational cost, achieving robust performance with limited resources as demonstrated on a real-world dataset.
Network traffic classification using machine learning techniques has been widely studied. Most existing schemes classify entire traffic flows, but there are major limitations to their practicality. At a network router, the packets need to be processed with minimum delay, so the classifier cannot wait until the end of the flow to make a decision. Furthermore, a complicated machine learning algorithm can be too computationally expensive to implement inside the router. In this paper, we introduce flow-packet hybrid traffic classification (FPHTC), where the router makes a decision per packet based on a routing policy that is designed through transferring the learned knowledge from a flow-based classifier residing outside the router. We analyze the generalization bound of FPHTC and show its advantage over regular packet-based traffic classification. We present experimental results using a real-world traffic dataset to illustrate the classification performance of FPHTC. We show that it is robust toward traffic pattern changes and can be deployed with limited computational resource.