On the robustness of resource allocation for parallel and distributed computing and communications

Shoukat Ali, Anthony A. Maciejewski, Howard Jay Siegel, Jong-Kook Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Performing computing and communication tasks on parallel and distributed systems may involve the coordinated use of different types of machines, networks, interfaces, and other resources. All of these resources should be allocated in a way that maximizes some system performance measure. However, allocation decisions and performance prediction are often based on "nominal" values of task and system parameters. The actual values of these parameters may differ from the nominal ones, e.g., because of inaccuracies in the initial estimation or because of changes over time caused by an unpredictable system environment. An important question then arises: given a system design, what extent of departure from the assumed circumstances will cause the quality of service to be unacceptably degraded? That is, how robust is the system? To address this problem, we have designed a methodology for deriving the degree of robustness of a resource allocation-the maximum amount of collective uncertainty in task and system parameters within which a user-specified level of performance can be guaranteed. We will illustrate our procedure by using it to derive robustness metrics for some example distributed systems. Furthermore, we will demonstrate the ability of the robustness metric to select the most robust resource allocation from among those that otherwise perform similarly (based on the primary performance criterion). This paper is for the Multiconference Keynote presentation to be given by H. J. Siegel.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications
EditorsH.R. Arabnia, Y. Mun, H.R. Arabnia, Y. Mun
Pages3-14
Number of pages12
Volume1
Publication statusPublished - 2003 Dec 1
Externally publishedYes
EventProceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications - Las Vegas, NV, United States
Duration: 2003 Jun 232003 Jun 26

Other

OtherProceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications
CountryUnited States
CityLas Vegas, NV
Period03/6/2303/6/26

Fingerprint

Distributed computer systems
Parallel processing systems
Resource allocation
Communication
Interfaces (computer)
Quality of service
Systems analysis
Uncertainty

Keywords

  • Clusters
  • Communication networks
  • Distributed computing
  • Embedded systems
  • Grids
  • Heterogeneous computing
  • Internet
  • Parallel computing
  • Reconfigurable systems
  • Resource allocation
  • Resource management systems
  • Robustness
  • Robustness metric
  • Scheduling
  • Wireless systems

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Ali, S., Maciejewski, A. A., Siegel, H. J., & Kim, J-K. (2003). On the robustness of resource allocation for parallel and distributed computing and communications. In H. R. Arabnia, Y. Mun, H. R. Arabnia, & Y. Mun (Eds.), Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (Vol. 1, pp. 3-14)

On the robustness of resource allocation for parallel and distributed computing and communications. / Ali, Shoukat; Maciejewski, Anthony A.; Siegel, Howard Jay; Kim, Jong-Kook.

Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications. ed. / H.R. Arabnia; Y. Mun; H.R. Arabnia; Y. Mun. Vol. 1 2003. p. 3-14.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ali, S, Maciejewski, AA, Siegel, HJ & Kim, J-K 2003, On the robustness of resource allocation for parallel and distributed computing and communications. in HR Arabnia, Y Mun, HR Arabnia & Y Mun (eds), Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications. vol. 1, pp. 3-14, Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, Las Vegas, NV, United States, 03/6/23.
Ali S, Maciejewski AA, Siegel HJ, Kim J-K. On the robustness of resource allocation for parallel and distributed computing and communications. In Arabnia HR, Mun Y, Arabnia HR, Mun Y, editors, Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications. Vol. 1. 2003. p. 3-14
Ali, Shoukat ; Maciejewski, Anthony A. ; Siegel, Howard Jay ; Kim, Jong-Kook. / On the robustness of resource allocation for parallel and distributed computing and communications. Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications. editor / H.R. Arabnia ; Y. Mun ; H.R. Arabnia ; Y. Mun. Vol. 1 2003. pp. 3-14
@inproceedings{c15cc9096971483daa45b3489f0505e5,
title = "On the robustness of resource allocation for parallel and distributed computing and communications",
abstract = "Performing computing and communication tasks on parallel and distributed systems may involve the coordinated use of different types of machines, networks, interfaces, and other resources. All of these resources should be allocated in a way that maximizes some system performance measure. However, allocation decisions and performance prediction are often based on {"}nominal{"} values of task and system parameters. The actual values of these parameters may differ from the nominal ones, e.g., because of inaccuracies in the initial estimation or because of changes over time caused by an unpredictable system environment. An important question then arises: given a system design, what extent of departure from the assumed circumstances will cause the quality of service to be unacceptably degraded? That is, how robust is the system? To address this problem, we have designed a methodology for deriving the degree of robustness of a resource allocation-the maximum amount of collective uncertainty in task and system parameters within which a user-specified level of performance can be guaranteed. We will illustrate our procedure by using it to derive robustness metrics for some example distributed systems. Furthermore, we will demonstrate the ability of the robustness metric to select the most robust resource allocation from among those that otherwise perform similarly (based on the primary performance criterion). This paper is for the Multiconference Keynote presentation to be given by H. J. Siegel.",
keywords = "Clusters, Communication networks, Distributed computing, Embedded systems, Grids, Heterogeneous computing, Internet, Parallel computing, Reconfigurable systems, Resource allocation, Resource management systems, Robustness, Robustness metric, Scheduling, Wireless systems",
author = "Shoukat Ali and Maciejewski, {Anthony A.} and Siegel, {Howard Jay} and Jong-Kook Kim",
year = "2003",
month = "12",
day = "1",
language = "English",
isbn = "1892512416",
volume = "1",
pages = "3--14",
editor = "H.R. Arabnia and Y. Mun and H.R. Arabnia and Y. Mun",
booktitle = "Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications",

}

TY - GEN

T1 - On the robustness of resource allocation for parallel and distributed computing and communications

AU - Ali, Shoukat

AU - Maciejewski, Anthony A.

AU - Siegel, Howard Jay

AU - Kim, Jong-Kook

PY - 2003/12/1

Y1 - 2003/12/1

N2 - Performing computing and communication tasks on parallel and distributed systems may involve the coordinated use of different types of machines, networks, interfaces, and other resources. All of these resources should be allocated in a way that maximizes some system performance measure. However, allocation decisions and performance prediction are often based on "nominal" values of task and system parameters. The actual values of these parameters may differ from the nominal ones, e.g., because of inaccuracies in the initial estimation or because of changes over time caused by an unpredictable system environment. An important question then arises: given a system design, what extent of departure from the assumed circumstances will cause the quality of service to be unacceptably degraded? That is, how robust is the system? To address this problem, we have designed a methodology for deriving the degree of robustness of a resource allocation-the maximum amount of collective uncertainty in task and system parameters within which a user-specified level of performance can be guaranteed. We will illustrate our procedure by using it to derive robustness metrics for some example distributed systems. Furthermore, we will demonstrate the ability of the robustness metric to select the most robust resource allocation from among those that otherwise perform similarly (based on the primary performance criterion). This paper is for the Multiconference Keynote presentation to be given by H. J. Siegel.

AB - Performing computing and communication tasks on parallel and distributed systems may involve the coordinated use of different types of machines, networks, interfaces, and other resources. All of these resources should be allocated in a way that maximizes some system performance measure. However, allocation decisions and performance prediction are often based on "nominal" values of task and system parameters. The actual values of these parameters may differ from the nominal ones, e.g., because of inaccuracies in the initial estimation or because of changes over time caused by an unpredictable system environment. An important question then arises: given a system design, what extent of departure from the assumed circumstances will cause the quality of service to be unacceptably degraded? That is, how robust is the system? To address this problem, we have designed a methodology for deriving the degree of robustness of a resource allocation-the maximum amount of collective uncertainty in task and system parameters within which a user-specified level of performance can be guaranteed. We will illustrate our procedure by using it to derive robustness metrics for some example distributed systems. Furthermore, we will demonstrate the ability of the robustness metric to select the most robust resource allocation from among those that otherwise perform similarly (based on the primary performance criterion). This paper is for the Multiconference Keynote presentation to be given by H. J. Siegel.

KW - Clusters

KW - Communication networks

KW - Distributed computing

KW - Embedded systems

KW - Grids

KW - Heterogeneous computing

KW - Internet

KW - Parallel computing

KW - Reconfigurable systems

KW - Resource allocation

KW - Resource management systems

KW - Robustness

KW - Robustness metric

KW - Scheduling

KW - Wireless systems

UR - http://www.scopus.com/inward/record.url?scp=1642412076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1642412076&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:1642412076

SN - 1892512416

VL - 1

SP - 3

EP - 14

BT - Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications

A2 - Arabnia, H.R.

A2 - Mun, Y.

A2 - Arabnia, H.R.

A2 - Mun, Y.

ER -