Immersive Volumetric Video Playback: Near-RT Resource Allocation and O-RAN-based Implementation

TL;DR

The paper tackles end-to-end latency in immersive volumetric video (ImViD) for XR by proposing a joint, near-real-time orchestration of radio, compute, and content resources within an O-RAN framework. It introduces a Weber–Fechner QoE model and formulates a mixed, high-dimensional optimization over per-frame content-hit ratio, O-Cloud compute, and gNB bandwidth/power, solved with a structured Soft Actor-Critic (SAC) approach called ImVol-DRL. The architecture leverages O-RAN components (O1/O2/A1/E2) and near-real-time xApps to coordinate per-user, per-frame decisions, validated through a 5G O-RAN prototype and Python-based simulations. Results show substantial reductions in motion-to-photon latency and improvements in QoE and fairness, demonstrating the practical viability of end-to-end radio–compute–content orchestration for latency-aware immersive streaming.

Abstract

Immersive volumetric video streaming in extended reality (XR) demands ultra-low motion-to-photon (MTP) latency, which conventional edge-centric architectures struggle to meet due to per-frame computationally intensive rendering tightly coupled with user motion. To address this challenge, we propose an Open Radio Access Network (O-RAN)-integrated playback framework that jointly orchestrates radio, compute, and content resources in near real time (Near-RT) control loop. The system formulates the rendered-pixel ratio as a continuous control variable and jointly optimizes it over the Open Cloud (O-Cloud) compute, gNB transmit power, and bandwidth under a Weber-Fechner quality of experience (QoE) model, explicitly balancing resolution, computation, and latency. A Soft Actor-Critic (SAC) agent with structured action decomposition and QoE-aware reward shaping resolves the resulting high-dimensional control problem. Experiments on a 5G O-RAN testbed and system simulations show that SAC reduces median MTP latency by above $11\%$ and improves both mean QoE and fairness, demonstrating the feasibility of RIC-driven joint radio-compute-content control for scalable, latency-aware immersive streaming.

Figures (12)

• Figure 1: ImViD playback workflow per frame.
• Figure 2: O-RAN functional split and E2AP control plane.
• Figure 3: Volumetric video reconstruction and playback flow.
• Figure 4: Report and control message interaction process.
• Figure 5: Reward evolution with 8 users under different policies.