With the development of mobile edge computing (MEC) and blockchain-based federated learning (BCFL), a number of studies suggest deploying BCFL on edge servers. In this case, resource-limited edge servers need to serve both mobile devices for their offloading tasks and the BCFL system for model training and blockchain consensus in a cost-efficient manner without sacrificing the service quality to any side. To address this challenge, this paper proposes a resource allocation scheme for edge servers, aiming to provide the optimal services with the minimum cost. Specifically, we first analyze the energy consumed by the MEC and BCFL tasks, and then use the completion time of each task as the service quality constraint. Then, we model the resource allocation challenge into a multivariate, multi-constraint, and convex optimization problem. To solve the problem in a progressive manner, we design two algorithms based on the alternating direction method of multipliers (ADMM) in both the homogeneous and heterogeneous situations with equal and on-demand resource distribution strategies, respectively. The validity of our proposed algorithms is proved via rigorous theoretical analysis. Through extensive experiments, the convergence and efficiency of our proposed resource allocation schemes are evaluated. To the best of our knowledge, this is the first work to investigate the resource allocation dilemma of edge servers for BCFL in MEC.
翻译:随着移动边缘计算(MEC)和基于链链的联结学习(BCFL)的发展,一些研究表明,在边缘服务器上部署BCFL(BCFL),在这种情况下,资源有限的边缘服务器需要以成本效益高的方式为移动设备提供卸载任务,为模型培训和链链共识提供BCFL(BCFL)系统提供模型培训和链链共识,同时不牺牲服务质量给任何方面。为了应对这一挑战,本文件提议为边缘服务器制定一个资源分配计划,旨在以最低成本提供最佳服务。具体地说,我们首先分析MEC和BCFL任务所消耗的能量,然后将每项任务的完成时间用作服务质量的制约。然后,我们将资源分配挑战建模成一个多变式、多节制和convex优化问题。为了以渐进的方式解决问题,我们设计了两种基于相互交替的乘数法(ADMMMM)的算法,分别以同等和按需的资源分配战略提供这种服务。我们提议的算法的有效性通过严格的理论分析得到证明。通过广泛的实验,我们拟议的MC资源分配机制中的拟议资源优势分配方法的最佳评估了我们对MBC公司资源分配安排的知识。