Fine-Grained Network Traffic Classification with Contextual QoS Profiling

TL;DR

This paper introduces a hierarchical graph neural network framework that improves fine-grained network traffic classification by incorporating QoS metrics, enabling better service differentiation and adaptive prioritization in dynamic environments.

Contribution

It presents a novel GNN-based approach with a three-level graph representation and an automated QoS-aware assignment algorithm for enhanced traffic classification.

Findings

Outperforms state-of-the-art methods in 14 usage scenarios

Effectively captures multi-scale temporal patterns in traffic data

Enhances service differentiation through QoS-aware classification

Abstract

Accurate network traffic classification is vital for managing modern applications with strict Quality of Service (QoS) demands, such as edge computing, real-time XR, and autonomous systems. While recent advances in application-level classification show high accuracy, they often miss fine-grained in-app QoS variations critical for service differentiation. This paper proposes a hierarchical graph neural network (GNN) framework that combines a three-level graph representation with an automated QoS-aware assignment algorithm. The model captures multi-scale temporal patterns via packet aggregation, time-window clustering, and session-level behavior modeling. QoS priorities are derived using five key metrics (bandwidth, jitter, packet stability, burst frequency, and burst stability), processed through logarithmic transformation and weighted ranking. Evaluations across 14 usage scenarios from YouTube, Prime Video, TikTok, and Zoom show that the proposed GNN significantly outperforms state-of-the-art methods in service-level classification. The QoS-aware assignment further refines classification to enhance user experience. This work advances QoS-aware traffic classification by enabling precise in-app usage differentiation and adaptive service prioritization in dynamic network environments.