arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09729cs.AIcs.SYeess.SY
收藏

移动边缘计算系统中面向定制化VR服务的联邦基于提示的决策Transformer

Federated Prompt-based Decision Transformer for Customized VR Services in Mobile Edge Computing System

Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology(香港科技大学跨学科研究学院);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学)

Tailin Zhou, Jiadong Yu, Jun Zhang, Danny H. K. Tsang

AI总结:

本文研究MEC系统中定制化VR服务的资源分配,提出FedPromptDT框架,结合联邦学习与基于提示的序列建模预训练通用决策模型,在保护隐私的同时提升模型对多样化用户环境的适应性。

摘要:

本文研究移动边缘计算(MEC)系统中的资源分配问题,以为异构用户提供定制化的虚拟现实(VR)服务。我们首先引入体验质量(QoE)指标来衡量用户体验,该指标考虑了MEC系统的延迟、用户注意力水平和偏好分辨率。然后,为资源分配制定了一个QoE最大化问题,以确保尽可能高的用户体验,该问题被转化为强化学习问题,旨在学习适用于所有MEC服务器上多样化用户环境的通用策略。为学习该通用策略,我们提出了一个采用联邦学习(FL)和基于提示的序列建模的框架,在MEC服务器间预训练一个通用决策模型,命名为FedPromptDT。使用FL解决了本地MEC数据不足的问题,同时在离线训练期间保护了用户隐私。整合用户环境线索和用户偏好分配的提示设计,提高了模型在在线执行期间对各种用户环境的适应性。

英文摘要:

This paper investigates resource allocation to provide heterogeneous users with customized virtual reality (VR) services in a mobile edge computing (MEC) system. We first introduce a quality of experience (QoE) metric to measure user experience, which considers the MEC system's latency, user attention levels, and preferred resolutions. Then, a QoE maximization problem is formulated for resource allocation to ensure the highest possible user experience,which is cast as a reinforcement learning problem, aiming to learn a generalized policy applicable across diverse user environments for all MEC servers. To learn the generalized policy, we propose a framework that employs federated learning (FL) and prompt-based sequence modeling to pre-train a common decision model across MEC servers, which is named FedPromptDT. Using FL solves the problem of insufficient local MEC data while protecting user privacy during offline training. The design of prompts integrating user-environment cues and user-preferred allocation improves the model's adaptability to various user environments during online execution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑