Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fine-Grained Network Traffic Classification with Contextual QoS Profiling

Huiwen Zhang, Feng Ye

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.

Fine-Grained Network Traffic Classification with Contextual QoS Profiling

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.
Paper Structure (16 sections, 12 equations, 6 figures, 4 tables)

This paper contains 16 sections, 12 equations, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. AI-based Network Traffic Classification
  4. Service Aware Network Traffic Classification
  5. Framework of the Hierarchical Graph Neural Network based NTC
  6. Graph Construction
  7. Hierarchical Graph Encoder and QoS-aware Classifier
  8. QoS Awareness NTC
  9. QoS Awareness Assignment
  10. QoS-aware Model Training and Inference
  11. Evaluation Results
  12. Data Collection
  13. Experimental Setup and Evaluation Metrics
  14. Performance Evaluation on QoS-Aware NTC
  15. More Discussion
  16. ...and 1 more sections

Figures (6)

  • Figure 1: Overview of the hierarchical GNN framework.
  • Figure 2: Overview of the graph encoder.
  • Figure 3: Overview of the QoS-aware classifier.
  • Figure 4: Example of the multi-level graph structure and the corresponding raw session traffic.
  • Figure 5: Normalized confusion matrices for baseline NTC, proposed QoS-aware NTC, and an existing packet-level NTC.
  • ...and 1 more figures