Abstract: Recently cloud computing has been widely used by researchers for executing scientific applications. Cloud offers resources in the form of virtual machines which are dynamically provisioned and released and comes with a usage cost. This gives an illusion of abundance of resources available for execution. Hence, efficient scheduling mechanisms which satisfy the various quality of service requirements while minimizing the cost are the need of the hour. Although, scheduling algorithms which map a deadline constrained workflow to a cloud while minimizing cost have been studied, most of the time the makespan of the optimal schedule returned will be less than the deadline. Hence, a fine tuning of the optimal schedule thus returned will be useful and has the advantage of minimizing the under utilization of resources thereby achieving savings in cost. This study proposes an expedite genetic algorithm with fine tuning for scheduling deadline constrained workflow applications onto a cloud.
S. Sindhu and Saswati Mukherjee, 2016. A Fine Tuned Expedite Evolutionary Approach for Scheduling Deadline Constrained Scientific Application in Cloud. Asian Journal of Information Technology, 15: 3268-3279.