DocumentCode :
2985666
Title :
On-line preemptive scheduling of real-time services with profit and penalty
Author :
Liu, Shuo ; Quan, Gang ; Ren, Shangping
Author_Institution :
Electr. & Comput. Eng. Dept., Florida Int. Univ., Miami, FL, USA
fYear :
2011
fDate :
17-20 March 2011
Firstpage :
287
Lastpage :
292
Abstract :
In this paper, we propose a new preemptive scheduling algorithm which belongs to a new family of real-time service oriented scheduling problems. As the complementarity of our previous non-preemptive algorithm, real time tasks are scheduled preemptively with the objective of maximizing the total utility this time. Different from the traditional utility accrual scheduling problem that each task is associated with only a single time utility function (TUF), two different TUFs - a profit TUF and a penalty TUF - are associated with each task, to model the real-time services that not only need to reward the early completions but also need to penalize the abortions or deadline misses. We present a preemptive scheduling heuristics to judiciously accept, schedule, and abort real-time services when necessary to maximize the accrued utility. The new scheduling algorithm has a much better performance than an earlier scheduling approach based on a similar model does. Our extensive experimental results show that our proposed preemptive algorithms can outperform the related non-preemptive counterpart, which is a significant improvement compared with the scheduling pair proposed by Yu et al..
Keywords :
cloud computing; real-time systems; scheduling; service-oriented architecture; task analysis; on-line preemptive scheduling; penalty; profit; real-time services; task scheduling; time utility function; Indexes; Measurement; Real time systems; Scheduling; Scheduling algorithm; Servers;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Southeastcon, 2011 Proceedings of IEEE
Conference_Location :
Nashville, TN
ISSN :
1091-0050
Print_ISBN :
978-1-61284-739-9
Type :
conf
DOI :
10.1109/SECON.2011.5752951
Filename :
5752951
Link To Document :
بازگشت