ResLearn: Transformer-based Residual Learning for Metaverse Network Traffic Prediction

Abstract

Our work proposes a comprehensive solution for predicting Metaverse network traffic, addressing the growing demand for intelligent resource management in eXtended Reality (XR) services. We first introduce a state-of-the-art testbed capturing a real-world dataset of virtual reality (VR), augmented reality (AR), and mixed reality (MR) traffic, made openly available for further research. To enhance prediction accuracy, we then propose a novel view-frame (VF) algorithm that accurately identifies video frames from traffic while ensuring privacy compliance, and we develop a Transformer-based progressive error-learning algorithm, referred to as ResLearn for Metaverse traffic prediction. ResLearn significantly improves time-series predictions by using fully connected neural networks to reduce errors, particularly during peak traffic, outperforming prior work by 99%. Our contributions offer Internet service providers (ISPs) robust tools for real-time network management to satisfy Quality of Service (QoS) and enhance user experience in the Metaverse.

Figures (6)

• Figure 1: System model of the proposed solution. $x$ in $f^x[t]$ represents one of the features. EDA is the exploratory data analysis.
• Figure 2: (a) PDF of packet lengths, and (b) PDF of inter-arrival time for a sample Metaverse traffic segment.
• Figure 3: ResLearn algorithm.
• Figure 4: Experimental platform used for data capture.
• Figure 5: frame size time series data with roll-over averaging window.