NEW QUEUING STRATEGIES EMPLOYING SERVICE INTERVAL-BASED PRIORITY FOR REAL-TIME COMMUNICATIONS IN ATM NETWORKS

Authors
Citation
Jw. Lee et Bg. Lee, NEW QUEUING STRATEGIES EMPLOYING SERVICE INTERVAL-BASED PRIORITY FOR REAL-TIME COMMUNICATIONS IN ATM NETWORKS, Annales des telecommunications, 50(7-8), 1995, pp. 617-623
Citations number
19
Categorie Soggetti
Telecommunications
ISSN journal
00034347
Volume
50
Issue
7-8
Year of publication
1995
Pages
617 - 623
Database
ISI
SICI code
0003-4347(1995)50:7-8<617:NQSESI>2.0.ZU;2-7
Abstract
In this paper, we propose queueing strategies employing the service in terval-based priority (sip) which can provide delay-bounded, and loss- free services, while maximizing bandwidth utilization in the ATM netwo rk. We also describe a variation of the sip, the residual service inte rval-based priority (RSIP) which can achieve almost full utilization b y assigning priorities dynamically on the basis of the residual servic e interval. We store the realtime cells belonging to different connect ions in logically separated queues, and for each queue, we set a param eter called service interval, during which only one cell is allowed to be transmitted. The sip server takes and transmits the head-of-line ( HOL) cell of the queue which has the smallest service interval, while the RSIP sewer selects the queue with the smallest residual service in terval. When there is no eligible real-time cell, it transmits non-rea l-time cell, thus enabling a maximized bandwidth utilization. Employin g the above queueing strategies, we analyze the delay characteristics deterministically with the leaky bucket bounded input traffic and then dimension the optimal service interval. In dimensioning the service i nterval and buffer space of each real-time ser-vice queue, we consider burstiness of traffic in conjunction with delay constraints, so that bandwidth utilization can get maximized. In addition, we consider the issues of protection from malicious users, average bandwidth utilizati on, and coupling between the delay bound and the bandwidth allocation granularity.