Non-Preemptive On-Line Scheduling of Real-Time Services with Task Migration for Cloud Computing

This paper, focuses on providing a solution for online scheduling problems of real-time service for cloud computing. The real time tasks are scheduled non-preemptively with the objective of maximizing the total utility. In traditional approach, the task is scheduled non-preemptively with two different types of Time Utility Functions (TUFs) - a profit (TUF) and a penalty (TUF), to form the real time applications for cloud computing that need not only to reward the early completions of a task but also penalize the abortions or deadline misses of real time tasks. This scheduling method judiciously aborts the task when it misses the deadline.