Fuzzy-GA Optimized Multi-Cloud Multi-Task Scheduler For Cloud Storage And Service Applications
Suresh Kumar V · 2013
Computing clusters have been one of the most popular platforms for solving Many Task Computing(MTC) problems, especially in the case of loosely coupled tasks. However, building and managing physical clusters exhibits several drawbacks:1)Major investments in hardware, specialized installations, and qualified personal; 2) Long periods of cluster under-utilization; 3)Cluster overloading and insufficient computational resources during peak demand periods. Regarding these limitations, cloud computing technology has been proposed to complement the in-house data-center infrastructure to satisfy peak workloads.In this paper, we explore this scenario to deploy a computing cluster on the top of a multi cloud infrastructure, for solving loosely coupled MTC Application. The benefits of Quality of Service (QoS) aware service selection is undisputed. The selection process based on QoS allows the user to specify their requirements not only based on functional attributes but also on nonfunctional attributes. The automation of this selection process can be done via optimization. Genetic algorithm is one such method that cans find approximate solutions during the service selection task