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

2025-10-25

AI Summary

To address the stringent requirements of future immersive XR applications—namely, high energy efficiency, ultra-low latency, and high-throughput wireless communication—this paper proposes a reinforcement learning–based framework for joint dynamic resource allocation and partial computation offloading. The framework co-optimizes uplink/downlink time-slot scheduling and edge offloading decisions, adapting dynamically to real-time network conditions and the computational capabilities of XR headsets. By explicitly modeling the trade-off between frame loss rate and energy efficiency, it identifies the optimal region for partial offloading. Experimental results demonstrate that, compared to baseline strategies of full or no offloading, the proposed method extends system coverage by 55% and reduces energy consumption by up to 34%, thereby significantly enhancing both communication performance and energy efficiency.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

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.

Problem

• Optimizing energy-efficient wireless communication for XR applications
• Dynamically allocating uplink and downlink resources with edge offloading
• Balancing frame loss rate and energy efficiency through partial offloading

Innovation

• Reinforcement learning framework for dynamic resource allocation
• Partial offloading decisions based on device capabilities
• Optimizing energy efficiency and frame loss rate tradeoff