Scalable Multiuser Immersive Communications with Multi-numerology and Mini-slot

TL;DR

This paper proposes a scalable resource allocation method for multiuser immersive XR communications using multi-numerology and mini-slots, employing deep reinforcement learning to optimize user experience.

Contribution

It introduces a novel flexible resource block configuration and applies deep reinforcement learning for adaptive, scalable resource allocation in heterogeneous XR networks.

Findings

Method achieves high efficiency in resource utilization.

Scalable approach adapts to diverse XR service demands.

Enhanced QoE for multiple users under constraints.

Abstract

This paper studies multiuser immersive communications networks in which different user equipment may demand various extended reality (XR) services. In such heterogeneous networks, time-frequency resource allocation needs to be more adaptive since XR services are usually multi-modal and latency-sensitive. To this end, we develop a scalable time-frequency resource allocation method based on multi-numerology and mini-slot. To appropriately determining the discrete parameters of multi-numerology and mini-slot for multiuser immersive communications, the proposed method first presents a novel flexible time-frequency resource block configuration, then it leverages the deep reinforcement learning to maximize the total quality-of-experience (QoE) under different users' QoE constraints. The results confirm the efficiency and scalability of the proposed time-frequency resource allocation method.