발간년도 : [2017]
| 논문정보 |
|
| 논문명(한글) |
[Vol.12, No.2] The Effect on Defering Degree of The Optional Tasks in The Imprecise On-Line Scheduling |
|
| 논문투고자 |
Gi-Hyeon Song |
|
| 논문내용 |
In a system that supports imprecise computations, every time-critical task is structured in such a way that it can be logically decomposed into two subtasks: a mandatory subtask and an optional subtask. In the imprecise computations, the on-line scheduling problems not only to improve schedulability for the mandatory subtasks but to minimize total error for the optional subtasks have been proposed recently. The NORA(No Off-line tasks and on-line tasks Ready upon Arrival) algorithm can find a schedule with the minimum total error for a task system consisting solely of on-line tasks that are ready upon arrival. To improve the schedulability of the NORA algorithm, The DOT(Deferred Optional Tasks) and the DOP(Deferable Optional Part) algorithms delay the optional subtasks of the earliest deadline tasks keeping the total error minimized. However, the algorithms were designed only for preemtable on-line imprecise tasks and couldn’t be applied for nonpreemtable tasks. So, the DOTMD(Delay Optional Tasks Meeting its Deadine) and the DOTMP(Delay Optional Tasks as Many as Possible) algorithms are proposed for scheduling the nonpreemtable imprecise on-line tasks to improve the schedulability by defering the optional subtasks also. But, the effects of the defering degree for the optional subtasks on the schedulability and the total error haven’t been known yet specifically until now. Therefore, in this paper, the effects of the defering degree not only for the preemtable but for the nonpreemtable optional subtasks on the schedulability and the total error are analyzed and compared respectively by simulation study. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
