Meta Computing is a new computing paradigm, which aims to solve the problem of computing islands in current edge computing paradigms and integrate all the resources on a network by incorporating cloud, edge, and particularly terminal-end devices. It throws light on solving the problem of lacking computing power. However, at this stage, due to technical limitations, it is impossible to integrate the resources of the whole network. Thus, we create a new meta computing architecture composed of multiple meta computers, each of which integrates the resources in a small-scale network. To make meta computing widely applied in society, the service quality and user experience of meta computing cannot be ignored. Consider a meta computing system providing services for users by scheduling meta computers, how to choose from multiple meta computers to achieve maximum Quality-of-Experience (QoE) with limited budgets especially when the true expected QoE of each meta computer is not known as a priori? The existing studies, however, usually ignore the costs and budgets and barely consider the ubiquitous law of diminishing marginal utility. In this paper, we formulate a resource scheduling problem from the perspective of the multi-armed bandit (MAB). To determine a scheduling strategy that can maximize the total QoE utility under a limited budget, we propose an upper confidence bound (UCB) based algorithm and model the utility of service by using a concave function of total QoE to characterize the marginal utility in the real world. We theoretically upper bound the regret of our proposed algorithm with sublinear growth to the budget. Finally, extensive experiments are conducted, and the results indicate the correctness and effectiveness of our algorithm.

翻译：元计算是一种新兴的计算范式，旨在通过融合云、边缘特别是终端设备，解决当前边缘计算范式中的计算孤岛问题，并整合网络中的所有资源。它为破解算力短缺难题提供了新思路。然而在当前阶段，受限于技术条件，尚无法实现全网资源的统一整合。为此，我们构建了一种由多个元计算机构成的新型元计算架构，每个元计算机负责整合小范围网络内的资源。为使元计算得以广泛应用，其服务质量与用户体验不容忽视。考虑一个通过调度元计算机为用户提供服务的元计算系统，在预算有限且各元计算机的真实预期体验质量（QoE）未知的情况下，如何从多个元计算机中选择以实现最大QoE？现有研究通常忽略成本与预算约束，且极少考虑普遍存在的边际效用递减规律。本文从多臂老虎机（MAB）视角构建了资源调度问题模型。为确定有限预算下能最大化总QoE效用的调度策略，我们提出了一种基于上置信界（UCB）的算法，并通过总QoE的凹函数对服务效用进行建模，以刻画现实世界中的边际效用特征。我们从理论上证明了所提算法的遗憾值上界与预算呈次线性增长。最后，通过大量实验验证了算法的正确性与有效性。