Bayesian Optimization for Task Offloading and Resource Allocation in Mobile Edge Computing
Bayesian Optimization for Task Offloading and Resource Allocation in Mobile Edge Computing
复制标题
DOI：
10.1109/ieeeconf56349.2022.10051868
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Jiahe Yan;Qin Lu;G. Giannakis
中科院分区：
文献类型：
--
作者：
Jiahe Yan;Qin Lu;G. Giannakis
近年来，移动的边缘计算（MEC）在包括物联网（IoT）的硬件受限的无线设备（WD）的计算能力的成本效益增强的前提下出现。在一般的多服务器多用户MEC系统中，每个WD具有要执行的计算任务，并且必须选择二进制（卸载）加载决策，沿着以在线方式的模拟幅度资源分配变量，目标是最小化具有动态系统状态的总能量延迟成本（EDC）。虽然过去的工作通常依赖于EDC函数的显式表达，但本贡献考虑了实际设置，其中代替系统状态信息，EDC函数不以分析形式提供，而是仅显示查询点处的函数值。为了解决这种具有挑战性的在线组合问题，只有强盗信息，新的贝叶斯优化（BO）的方法，提出了利用多臂强盗（MAB）框架。每个时隙，通过利用时间信息，离散的卸载决定，首先获得通过MAB方法，和模拟资源分配变量，随后使用BO选择规则进行优化。数值试验验证了所提出的BO方法的有效性。
Recent years have witnessed the emergence of mobile edge computing (MEC), on the premise of a costeffective enhancement in the computational ability of hardware-constrained wireless devices (WDs) comprising the Internet of Things (IoT). In a general multi-server multi-user MEC system, each WD has a computational task to execute and has to select binary (off)loading decisions, along with the analog-amplitude resource allocation variables in an online manner, with the goal of minimizing the overall energy-delay cost (EDC) with dynamic system states. While past works typically rely on the explicit expression of the EDC function, the present contribution considers a practical setting, where in lieu of system state information, the EDC function is not available in analytical form, and instead only the function values at queried points are revealed. Towards tackling such a challenging online combinatorial problem with only bandit information, novel Bayesian optimization (BO) based approach is put forth by leveraging the multi-armed bandit (MAB) framework. Per time slot, by exploiting temporal information, the discrete offloading decisions are first obtained via the MAB method, and the analog resource allocation variables are subsequently optimized using the BO selection rule. Numerical tests validate the effectiveness of the proposed BO approach.