GWO Based Task Allocation for Load Balancing in Containerized Cloud

Abstract

On-demand provisioning of computing services such as analytics, intelligence, networking, storage, and servers, etc. over the internet is the main function of cloud computing. Several servers are connected in a distributed manner over the internet to execute tasks. Recently, container technology has gained enormous popularity as it can improve overall applica-tion performance by providing OS-level virtualization in cloud computing systems. Based on the resources available on server, a server can accommodate more than one container running on it. The process of distributing the incoming requests or user tasks among all available servers in such a way that all the servers will have almost equal workload is called load balancing. In this paper, we proposed a Grey Wolf Optimization(GWO) based technique for load distribution in the containerized cloud and also to reduce the makespan. We have compared our results with the Genetic algorithm and Particle Swarm Optimization(PSO) based algorithm. The experimental result indicate that the GWO based technique is performing better in terms of load balancing and also having reduced makespan.