Online Layer-Aware Joint Request Scheduling, Container Placement, and Resource Provision in Edge Computing

Containers have emerged as a pivotal tool for service deployment in edge computing. Before running the container, an image composed of several layers must exist locally. Recent strategies have utilized layer-sharing in images to reduce deployment delays. However, existing research only focuses on a single aspect of container orchestration, like container placement, neglecting the joint optimization of the entire orchestration process. To fill in such gaps, this article introduces an online strategy that considers layer-aware container orchestration, encompassing request scheduling, container placement, and resource provision. The goal is to reduce costs, adapt to evolving user demands, and adhere to system constraints. We present an online optimization problem that accounts for various real-world factors in orchestration, including container and server expenses. An online algorithm is proposed, integrating a regularization-based approach and stepwise rounding to address this optimization problem efficiently. The regularization approach separates time-dependent container placement and server wake-up costs, requiring only current information and past decisions. The stepwise rounding process generates feasible solutions that meet system constraints, reducing computational costs. Additionally, a competitive ratio proof is provided for the proposed algorithm. Extensive evaluations demonstrate that our approach achieves about 20% performance enhancement compared to baseline algorithms.

I. Introduction

Edge computing leverages various clusters deployed at the edge of the network [1], thereby significantly enhancing the capabilities of the core network to support data-intensive and delay-sensitive applications [2], [3]. To enable efficient service deployment at the edge, container technology has emerged as a solution for hosting services [4], [5], [6], [7]. A container-based service bundles all essential components into its container image, which comprises layers representing changes to the file system, including additions, deletions, and modifications [8]. Upon receiving a user request, it is scheduled to the edge cluster, where the container is placed, and the necessary resources are provisioned to run the container. If the edge cluster lacks the locally stored layers of the container image, they must be downloaded from a remote cloud-based registry [9], [10]. Hence, to deliver services to users through containers, container orchestration is essential, involving the following three main steps: 1) Scheduling user requests, 2) Placing containers in edge clusters, and 3) Provisioning resources in edge clusters.