Adaptive Containerization for Microservices in Distributed Cloud Systems

Abstract

The traditional monolithic on-premises model of application deployment is fast being replaced by a cloud-based microservices paradigm, driven in part by the rise of numerous cloud infrastructure providers providing seamless access to a variety of computing hardware, and the need for applications to serve an ever-increasing audience necessitating scalability. While container-based virtualization has been the preferred method of microservice deployment, Cloud Consumers have not had much opportunity for cost and resource optimization thus far. To this end, this paper introduces a resource allocation framework for the containerized deployment of microservices, called Adaptive Containerization for Microservices in Distributed Cloud Systems, which helps reduce operating costs while ensuring a minimum guaranteed level of service. Further, a variety of performance evaluation metrics have been provided to reinforce the validity of the proposed framework.