Share Email Print
cover

Proceedings Paper

Fundamental trade-offs in aggregate packet scheduling
Author(s): Zhi-Li Zhang; Zhenhai Duan; Yiwei Thomas Hou
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper we investigate the fundamental trade-offs in aggregate packet scheduling for support of guaranteed delay service. In particular, we study the relationships between the worst-case edge-to-edge delay (i.e., the maximum delay experienced by any packet across a network domain), the (maximum) allowable link utilization level of a network and the ``sophistication/complexity'' of aggregate packet scheduling employed by a network. In our study, besides the simple FIFO packet scheduling algorithm, we consider two classes of aggregate packet scheduling algorithms: the static earliest time first} (SETF) and dynamic earliest time first (DETF). In both classes additional control information is encoded in the packet header for scheduling purpose: in the class of SETF, packets are stamped with its entry time at the network edge, and they are scheduled in the order of their (network entry) time stamps at a router; in the class of DETF, the packet time stamps are modified at certain routers as packets traverse them. Through these two classes of aggregate packet scheduling, we show that, with additional time stamp control information encoded in the packet header for scheduling purpose, we can significantly increase the (maximum) allowable link utilization level of a network, and at the same time reduce the worst-case edge-to-edge delay bound. These results illustrate the fundamental trade-offs in aggregate packet scheduling algorithms and shed light on their provisioning power in support of guaranteed delay service.

Paper Details

Date Published: 25 July 2001
PDF: 10 pages
Proc. SPIE 4526, Scalability and Traffic Control in IP Networks, (25 July 2001); doi: 10.1117/12.434407
Show Author Affiliations
Zhi-Li Zhang, Univ. of Minnesota/Twin Cities (United States)
Zhenhai Duan, Univ. of Minnesota/Twin Cities (United States)
Yiwei Thomas Hou, Fujitsu Labs. of America (United States)


Published in SPIE Proceedings Vol. 4526:
Scalability and Traffic Control in IP Networks
Sonia Fahmy; Kihong Park, Editor(s)

© SPIE. Terms of Use
Back to Top