Application deployment using containers with auto-scaling for microservices in cloud environment

Abstract

A microservice-based application is composed of a set of small services that run within their own processes and communicate with a lightweight mechanism. Processing the microservices efficiently with minimum processing time and cost, while utilizing the computing resources efficiently, is a challenging task in a cloud environment. To address this challenge, in this paper, we propose a new container-aware application scheduling strategy with an auto-scaling policy. The proposed strategy deploys the requested applications on the best-fit lightweight containers, with minimum deployment time, based on the resource requirements. Another important issue of the container-aware cloud environment is the cold start effect, which is solved using a rule-based policy in the proposed work for minimizing deployment time and cost of the applications. Furthermore, a dynamic bin-packing strategy is designed for deploying the applications to the minimum number of physical machines (PMs) with efficient utilization of the computing resources. Finally, a heuristic-based auto-scaling policy has been designed for minimizing the wastage of the computing resources in the cloud data center. Through numerical evaluation, we have shown the superiority of the proposed method over the existing state-of-the-art algorithms in terms of processing time, processing cost, resource utilization, and required numbers of PMs.