GPS schedulers and gaussian traffic

Petteri Mannersalo; Ilkka Norros

doi:10.1109/INFCOM.2002.1019419

GPS schedulers and gaussian traffic

Petteri Mannersalo, Ilkka Norros

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

34 Citations (Scopus)

Abstract

This article considers Gaussian flows which are fed into a GPS (Generalized Processor Sharing) scheduler. The system is analyzed using a most probable path approach. This method gives quite good approximations for performance measures, like queue length distributions in the full range of queue levels. The approximations are based on the distinction whether it is more probable that an aggregated queue consists of traffic from one class only or whether it is a combination of several classes. The approximate queue length distribution for a specific flow is then calculated either using the Empty Buffer Approximation or the authors' Rough Full Link Approximation, respectively.

Original language	English
Title of host publication	21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	1660-1667
ISBN (Print)	0-7803-7476-2
DOIs	https://doi.org/10.1109/INFCOM.2002.1019419
Publication status	Published - 2002
MoE publication type	A4 Article in a conference publication
Event	21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002 - New York, United States Duration: 23 Jun 2002 → 27 Jun 2002

Publication series

Series	Proceedings - IEEE INFOCOM
Volume	21
ISSN	0743-166X

Conference

Conference	21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002
Country/Territory	United States
City	New York
Period	23/06/02 → 27/06/02

Access to Document

10.1109/INFCOM.2002.1019419

https://publications.vtt.fi/julkaisut/muut/2002/Mannersalo_Norros.pdf

Cite this

@inproceedings{ef0b0b873d444609b0e22caac487d6be,

title = "GPS schedulers and gaussian traffic",

abstract = "This article considers Gaussian flows which are fed into a GPS (Generalized Processor Sharing) scheduler. The system is analyzed using a most probable path approach. This method gives quite good approximations for performance measures, like queue length distributions in the full range of queue levels. The approximations are based on the distinction whether it is more probable that an aggregated queue consists of traffic from one class only or whether it is a combination of several classes. The approximate queue length distribution for a specific flow is then calculated either using the Empty Buffer Approximation or the authors' Rough Full Link Approximation, respectively.",

author = "Petteri Mannersalo and Ilkka Norros",

note = "Project code: T1SU00227; 21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002 ; Conference date: 23-06-2002 Through 27-06-2002",

year = "2002",

doi = "10.1109/INFCOM.2002.1019419",

language = "English",

isbn = "0-7803-7476-2",

series = "Proceedings - IEEE INFOCOM",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

pages = "1660--1667",

booktitle = "21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002",

address = "United States",

}

Mannersalo, P & Norros, I 2002, GPS schedulers and gaussian traffic. in 21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002. IEEE Institute of Electrical and Electronic Engineers, Proceedings - IEEE INFOCOM, vol. 21, pp. 1660-1667, 21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002, New York, New York, United States, 23/06/02. https://doi.org/10.1109/INFCOM.2002.1019419

GPS schedulers and gaussian traffic. / Mannersalo, Petteri; Norros, Ilkka.
21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002. IEEE Institute of Electrical and Electronic Engineers, 2002. p. 1660-1667 (Proceedings - IEEE INFOCOM, Vol. 21).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - GPS schedulers and gaussian traffic

AU - Mannersalo, Petteri

AU - Norros, Ilkka

N1 - Project code: T1SU00227

PY - 2002

Y1 - 2002

N2 - This article considers Gaussian flows which are fed into a GPS (Generalized Processor Sharing) scheduler. The system is analyzed using a most probable path approach. This method gives quite good approximations for performance measures, like queue length distributions in the full range of queue levels. The approximations are based on the distinction whether it is more probable that an aggregated queue consists of traffic from one class only or whether it is a combination of several classes. The approximate queue length distribution for a specific flow is then calculated either using the Empty Buffer Approximation or the authors' Rough Full Link Approximation, respectively.

AB - This article considers Gaussian flows which are fed into a GPS (Generalized Processor Sharing) scheduler. The system is analyzed using a most probable path approach. This method gives quite good approximations for performance measures, like queue length distributions in the full range of queue levels. The approximations are based on the distinction whether it is more probable that an aggregated queue consists of traffic from one class only or whether it is a combination of several classes. The approximate queue length distribution for a specific flow is then calculated either using the Empty Buffer Approximation or the authors' Rough Full Link Approximation, respectively.

U2 - 10.1109/INFCOM.2002.1019419

DO - 10.1109/INFCOM.2002.1019419

M3 - Conference article in proceedings

SN - 0-7803-7476-2

T3 - Proceedings - IEEE INFOCOM

SP - 1660

EP - 1667

BT - 21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002

Y2 - 23 June 2002 through 27 June 2002

ER -

GPS schedulers and gaussian traffic

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this