Title :
Admission control and preemption policy design of multi-class computer networks
Author :
Zhao, Zhen ; Weber, Steven ; De Oliveira, Jaudelice C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
Abstract :
The subject of optimal admission control for maximizing revenue in multiclass loss networks has been well studied. Preemption policies, employed in the Differentiated Services network architecture, serve as an additional type of loss network control, where active low priority calls may be selectively preempted upon the arrival of a high priority call. This paper studies the joint use of admission control and preemption for a two class loss link where per-class revenues are earned per unit time for each active call, and an instantaneous preemption cost is incurred whenever the preemption mechanism is employed. Our main result is if the preemption cost is not too high then the system revenue under the optimal preemption policy with no admission control (complete sharing) exceeds that of the optimal admission control policy with no preemption. That is, preemption control is superior to admission control provided the preemption cost is not too high. Results are established via dynamic programming.
Keywords :
DiffServ networks; dynamic programming; telecommunication congestion control; complete sharing; differentiated services network architecture; dynamic programming; instantaneous preemption cost; loss network control; multiclass computer networks; multiclass loss networks; optimal admission control; optimal preemption policy; preemption policy design; Admission control; Circuits; Computer architecture; Computer networks; Cost function; Design engineering; Diffserv networks; Dynamic programming; Random variables; Web and internet services; admission control; coordinate convex; dynamic programming; loss network; preemption;
Conference_Titel :
Information Sciences and Systems (CISS), 2010 44th Annual Conference on
Conference_Location :
Princeton, NJ
Print_ISBN :
978-1-4244-7416-5
Electronic_ISBN :
978-1-4244-7417-2
DOI :
10.1109/CISS.2010.5464837