Resource Allocation for XR with Edge Offloading: A Reinforcement Learning Approach

TL;DR

This work tackles the challenge of maintaining low frame loss and energy efficiency for XR over wireless links by introducing a DQN-based reinforcement learning framework that jointly optimizes uplink/downlink slot allocation and partial edge offloading. The method models frame-level latency and energy via rates $R_t^{\mathrm{UL}}$, $R_t^{\mathrm{DL}}$, and edge/local processing times, and uses a state defined by $(D_f^{\mathrm{UL}}, D_f^{\mathrm{DL}}, h_f)$ and actions that discretize $N_f^{\mathrm{UL}}$, $N_f^{\mathrm{DL}}$, and $\alpha_f$. Key findings show that partial offloading extends network coverage and reduces energy consumption relative to baseline always/never offloading, with performance improving when headset computing capability and bandwidth are favorable. The approach provides a practical, RL-driven framework for adaptive XR resource management in urban macro-cell environments, with potential extensions to multi-user scenarios.

Abstract

Future immersive XR applications will require energy-efficient, high data rate, and low-latency wireless communications in uplink and downlink. One of the key considerations for supporting such XR applications is intelligent and adaptive resource allocation with edge offloading. To address these demands, this paper proposes a reinforcement learning-based resource allocation framework that dynamically allocates uplink and downlink slots while making offloading decisions based on the XR headset's capabilities and network conditions. The paper presents a numerical analysis of the tradeoff between frame loss rate (FLR) and energy efficiency, identifying decision regions for partial offloading to optimize performance. Results show that for the used set of system parameters, partial offloading can extend the coverage area by 55% and reduce energy consumption by up to 34%, compared to always or never offloading. The results demonstrate that the headset's local computing capability plays a crucial role in offloading decisions. Higher computing abilities enable more efficient local processing, reduce the need for offloading, and enhance energy savings.

Figures (4)

• Figure 1: Mean offloading ratio as a function of distance for different local execution capabilities.
• Figure 2: Mean energy consumption as a function of distance for different offloading methods.
• Figure 3: Example of offloading decision regions based on the distance.
• Figure 4: Mean offloading ratio as a function of distance for varying bandwidths.