Adaptive Cooperative Streaming of Holographic Video Over Wireless Networks: A Proximal Policy Optimization Solution

TL;DR

The paper addresses the challenge of streaming holographic video over wireless networks, where high data-rate requirements and dynamic channels can severely impact QoE. It introduces a cooperative holographic streaming framework with 3D tiling and a novel QoE metric that captures video quality, fluctuations, and rebuffering, and formulates a non-convex MINLP to maximize QoE by jointly optimizing beamforming, bitrate levels, and compression indicators. The problem is solved by decomposing into a convex beamforming subproblem solved via CVX and a learning-based bitrate/compression subproblem solved with Proximal Policy Optimization (PPO); the ECS acts as the RL agent, with states, actions, and rewards defined to drive QoE optimization. Simulation results with multiple APs and users show that the PPO-based scheme significantly outperforms baselines, with QoE improving as bandwidth, slot duration, or device capacity increase. The work demonstrates a practical pathway to improve holographic streaming QoE in wireless networks and suggests future AI-driven interference management enhancements.

Abstract

Adapting holographic video streaming to fluctuating wireless channels is essential to maintain consistent and satisfactory Quality of Experience (QoE) for users, which, however, is a challenging task due to the dynamic and uncertain characteristics of wireless networks. To address this issue, we propose a holographic video cooperative streaming framework designed for a generic wireless network in which multiple access points can cooperatively transmit video with different bitrates to multiple users. Additionally, we model a novel QoE metric tailored specifically for holographic video streaming, which can effectively encapsulate the nuances of holographic video quality, quality fluctuations, and rebuffering occurrences simultaneously. Furthermore, we formulate a formidable QoE maximization problem, which is a non-convex mixed integer nonlinear programming problem. Using proximal policy optimization (PPO), a new class of reinforcement learning algorithms, we devise a joint beamforming and bitrate control scheme, which can be wisely adapted to fluctuations in the wireless channel. The numerical results demonstrate the superiority of the proposed scheme over representative baselines.

Figures (5)

• Figure 1: System model.
• Figure 2: Convergence of Algorithm 1.
• Figure 3: QoE versus $W$.
• Figure 4: QoE versus $\tau$.
• Figure 5: QoE versus $C_{\rm max}$.