In the edge-cloud continuum, datacenters provide microservices (MSs) to mobile users, with each MS having specific latency constraints and computational requirements. Deploying such a variety of MSs matching their requirements with the available computing resources is challenging. In addition, time-critical MSs may have to be migrated as the users move, to keep meeting their latency constraints. Unlike previous work relying on a central orchestrator with an always-updated global view of the available resources and of the users' locations, this work envisions a distributed solution to the above issues. In particular, we propose a distributed asynchronous protocol for MS deployment in the cloud-edge continuum that (i) dramatically reduces the system overhead compared to a centralized approach, and (ii) increases the system stability by avoiding having a single point of failure as in the case of a central orchestrator. Our solution ensures cost-efficient feasible placement of MSs, while using negligible bandwidth.

翻译：在边缘-云连续体中，数据中心为移动用户提供微服务（MS），每个微服务具有特定的延迟约束和计算需求。将这类多样化的微服务与可用计算资源进行匹配部署具有挑战性。此外，当用户移动时，时间关键型微服务可能需要迁移以持续满足其延迟约束。与以往依赖集中式编排器（始终保持对可用资源和用户位置的全局视图）的工作不同，本研究针对上述问题提出了一种分布式解决方案。具体而言，我们提出了一种用于云-边缘连续体中微服务部署的分布式异步协议，该协议（i）与集中式方法相比显著降低了系统开销，（ii）通过避免集中式编排器存在的单点故障问题，增强了系统稳定性。本方案在保证微服务低成本可行部署的同时，占用的带宽可忽略不计。