Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
复制标题
DOI：
10.1109/jsac.2021.3126075
复制
发表时间：
2022-01-01
影响因子：
16.4
通讯作者：
Ji, Yusheng
中科院分区：
文献类型：
--
作者：
Chen, Xianfu;Wu, Celimuge;Ji, Yusheng
本文研究了一种由基础设施提供商（InP）部署的空地集成多访问边缘计算系统。根据与InP的商业协议，第三方服务提供商向订阅的移动的用户（MU）提供计算服务。MU随着时间的推移竞争共享频谱和计算资源以实现其独特的目标。从MU的角度来看，我们特意定义了更新的年龄，以捕获更新计算结果中的信息陈旧。考虑到系统动力学，我们将MU之间的相互作用建模为随机博弈。在没有合作的纳什均衡中，每个MU的行为与当地系统的状态和结构一致。因此，我们可以将随机博弈转化为单主体马尔可夫决策过程。作为另一个主要贡献，我们开发了一种在线深度强化学习（RL）方案，该方案采用两个独立的双深度Q网络分别近似Q因子和决策后Q因子。深度RL方案允许每个MU优化具有未知动态统计的行为。数值实验表明，我们提出的计划优于基线的平均效用在各种系统条件下。
This paper investigates an air-ground integrated multi-access edge computing system, which is deployed by an infrastructure provider (InP). Under a business agreement with the InP, a third-party service provider provides computing services to the subscribed mobile users (MUs). MUs compete for the shared spectrum and computing resources over time to achieve their distinctive goals. From the perspective of an MU, we deliberately define the age of update to capture the staleness of information from refreshing computation outcomes. Given the system dynamics, we model the interactions among MUs as a stochastic game. In the Nash equilibrium without cooperation, each MU behaves in accordance with the local system states and conjectures. We can hence transform the stochastic game into a single-agent Markov decision process. As another major contribution, we develop an online deep reinforcement learning (RL) scheme that adopts two separate double deep Q-networks to approximate the Q-factor and the post-decision Q-factor, respectively. The deep RL scheme allows each MU to optimize the behaviours with unknown dynamic statistics. Numerical experiments show that our proposed scheme outperforms the baselines in terms of the average utility under various system conditions.