用强化学习优化XR设备多任务推理能耗，省电超四成。
Energy Optimization of Multi-task DNN Inference in MEC-assisted XR Devices: A Lyapunov-Guided Reinforcement Learning Approach
- 设计双时域联合优化策略，分层调度模型与资源
- 提出LyaPPO算法，在不同资源下省电24.79%~46.14%
- 适合边缘计算与轻量XR设备能效优化场景
扩展现实（XR）融合虚拟与真实世界，是未来网络的关键应用。尽管人工智能提升XR能力，却也给轻量级XR设备带来显著的计算与能耗挑战。本文构建了多任务深度神经网络（DNN）推理的分布式队列模型，解决资源竞争与队列耦合问题。针对XR设备高能耗与资源受限的难题，提出一种双时域联合优化策略，用于模型分割与资源分配，将其建模为双层优化问题，旨在最小化设备总能耗的同时保障队列稳定并满足计算与通信资源约束。为此，设计了一种基于李雅普诺夫引导的近端策略优化算法（LyaPPO）。数值结果表明，该算法优于基线方法，在不同资源容量下实现24.79%至46.14%的节能效果；相较于基线算法，设备能耗降低24.29%至56.62%。
原文摘要 · Abstract (English)
Extended reality (XR), blending virtual and real worlds, is a key application of future networks. While AI advancements enhance XR capabilities, they also impose significant computational and energy challenges on lightweight XR devices. In this paper, we developed a distributed queue model for multi-task DNN inference, addressing issues of resource competition and queue coupling. In response to the challenges posed by the high energy consumption and limited resources of XR devices, we designed a dual time-scale joint optimization strategy for model partitioning and resource allocation, formulated as a bi-level optimization problem. This strategy aims to minimize the total energy consumption of XR devices while ensuring queue stability and adhering to computational and communication resource constraints. To tackle this problem, we devised a Lyapunov-guided Proximal Policy Optimization algorithm, named LyaPPO. Numerical results demonstrate that the LyaPPO algorithm outperforms the baselines, achieving energy conservation of 24.79% to 46.14% under varying resource capacities. Specifically, the proposed algorithm reduces the energy consumption of XR devices by 24.29% to 56.62% compared to baseline algorithms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。