For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Call Admission Control on Single Node Networks under Output Rate-Controlled Generalized Processor Sharing (ORC-GPS) Scheduler
IEICE TRANSACTIONS on Communications
Publication Date: 2012/02/01
Online ISSN: 1745-1345
Print ISSN: 0916-8516
Type of Manuscript: PAPER
QoS, generalized processor sharing, output rate-controlled generalized processor sharing, call admission control, deterministic delay guarantee,
Full Text: PDF>>
Multimedia applications such as music or video streaming, video teleconferencing and IP telephony are flourishing in packet-switched networks. Applications that generate such real-time data can have very diverse quality-of-service (QoS) requirements. In order to guarantee diverse QoS requirements, the combined use of a packet scheduling algorithm based on Generalized Processor Sharing (GPS) and leaky bucket traffic regulator is the most successful QoS mechanism. GPS can provide a minimum guaranteed service rate for each session and tight delay bounds for leaky bucket constrained sessions. However, the delay bounds for leaky bucket constrained sessions under GPS are unnecessarily large because each session is served according to its associated constant weight until the session buffer is empty. In order to solve this problem, a scheduling policy called Output Rate-Controlled Generalized Processor Sharing (ORC-GPS) was proposed in . ORC-GPS is a rate-based scheduling like GPS, and controls the service rate in order to lower the delay bounds for leaky bucket constrained sessions. In this paper, we propose a call admission control (CAC) algorithm for ORC-GPS, for leaky-bucket constrained sessions with deterministic delay requirements. This CAC algorithm for ORC-GPS determines the optimal values of parameters of ORC-GPS from the deterministic delay requirements of the sessions. In numerical experiments, we compare the CAC algorithm for ORC-GPS with one for GPS in terms of schedulable region and computational complexity.