Discern-XR: An Online Classifier for Metaverse Network Traffic

TL;DR

An exclusive Metaverse network traffic classifier, named Discern-XR, to help Internet service providers (ISP) and router manufacturers enhance the quality of Metaverse services and contributes to the real-world Metaverse dataset, providing a comprehensive benchmark.

Abstract

In this paper, we design an exclusive Metaverse network traffic classifier, named Discern-XR, to help Internet service providers (ISP) and router manufacturers enhance the quality of Metaverse services. Leveraging segmented learning, the Frame Vector Representation (FVR) algorithm and Frame Identification Algorithm (FIA) are proposed to extract critical frame-related statistics from raw network data having only four application-level features. A novel Augmentation, Aggregation, and Retention Online Training (A2R-OT) algorithm is proposed to find an accurate classification model through online training methodology. In addition, we contribute to the real-world Metaverse dataset comprising virtual reality (VR) games, VR video, VR chat, augmented reality (AR), and mixed reality (MR) traffic, providing a comprehensive benchmark. Discern-XR outperforms state-of-the-art classifiers by 7% while improving training efficiency and reducing false-negative rates. Our work advances Metaverse network traffic classification by standing as the state-of-the-art solution.

Figures (6)

• Figure 1: Overview of the proposed solution. (a) Metaverse testbed to capture Metaverse network traffic, and (b) block diagram of the Discern-XR solution.
• Figure 2: (a) PDF of packet lengths, and (b) PDF of inter-arrival time for a sample Metaverse traffic segment.
• Figure 3: Vectorization of traffic segment using FVR algorithm. Representing statistical frame vector $\bm{v}_i$ for the $i$th segment. Diagram shows the representation of FVR for 15th and 115th segment from VR Game.
• Figure 4: (a) Histogram of frame count (g), average frame inter-arrival time (h), total frame duration (i) for 115th segment of VR Chat service, and (b) Histogram of frame count (g), average frame inter-arrival time (h), total frame duration (i) for 115th segment of VR Game service. Chat service shows many small frames (g) with scattered inter-arrival time (h) and duration (i). Game service shows larger frames (g) with many packets with small inter-arrival time (h) and smaller duration (i). Therefore, frame-related information provides unique information for superior classification.
• Figure 5: Results for the multi-class classifier for different experiments given Table \ref{['table:exppss']}.