The impact of predictive inaccuracies on execution scheduling

Research output: Contribution to journalArticlepeer-review

Standard

The impact of predictive inaccuracies on execution scheduling. / Jarvis, Stephen A.; He, Ligang; Spooner, Daniel P.; Nudd, Graham R.

In: Performance Evaluation, Vol. 60, No. 1-4, 05.2005, p. 127-139.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Jarvis, Stephen A. ; He, Ligang ; Spooner, Daniel P. ; Nudd, Graham R. / The impact of predictive inaccuracies on execution scheduling. In: Performance Evaluation. 2005 ; Vol. 60, No. 1-4. pp. 127-139.

Bibtex

@article{6e156469e155469fac9d9ea93cc02fa1,
title = "The impact of predictive inaccuracies on execution scheduling",
abstract = "This paper investigates the underlying impact of predictive inaccuracies on execution scheduling, with particular reference to execution time predictions. This study is conducted from two perspectives: from that of job selection and from that of resource allocation, both of which are fundamental components in execution scheduling. A new performance metric, termed the degree of misperception, is introduced to express the probability that the predicted execution times of jobs display different ordering characteristics from their real execution times due to inaccurate prediction. Specific formulae are developed to calculate the degree of misperception in both job selection and resource allocation scenarios. The parameters which influence the degree of misperception are also extensively investigated. The results presented in this paper are of significant benefit to scheduling approaches that take into account predictive data; the results are also of importance to the application of these scheduling techniques to real-world high-performance systems.",
keywords = "Execution time, Job selection, Performance evaluation, Performance prediction, Resource allocation, Scheduling",
author = "Jarvis, {Stephen A.} and Ligang He and Spooner, {Daniel P.} and Nudd, {Graham R.}",
note = "Funding Information: This work is sponsored in part by grants from the NASA AMES Research Center (administrated by USARDSG, Contract No. N68171-01-C-9012), the EPSRC (Contract No. GR/R47424/01) and the EPSRC e-Science Core Programme (Contract No. GR/S03058/01). ",
year = "2005",
month = may,
doi = "10.1016/j.peva.2004.10.015",
language = "English",
volume = "60",
pages = "127--139",
journal = "Performance Evaluation",
issn = "0166-5316",
publisher = "Elsevier",
number = "1-4",

}

RIS

TY - JOUR

T1 - The impact of predictive inaccuracies on execution scheduling

AU - Jarvis, Stephen A.

AU - He, Ligang

AU - Spooner, Daniel P.

AU - Nudd, Graham R.

N1 - Funding Information: This work is sponsored in part by grants from the NASA AMES Research Center (administrated by USARDSG, Contract No. N68171-01-C-9012), the EPSRC (Contract No. GR/R47424/01) and the EPSRC e-Science Core Programme (Contract No. GR/S03058/01).

PY - 2005/5

Y1 - 2005/5

N2 - This paper investigates the underlying impact of predictive inaccuracies on execution scheduling, with particular reference to execution time predictions. This study is conducted from two perspectives: from that of job selection and from that of resource allocation, both of which are fundamental components in execution scheduling. A new performance metric, termed the degree of misperception, is introduced to express the probability that the predicted execution times of jobs display different ordering characteristics from their real execution times due to inaccurate prediction. Specific formulae are developed to calculate the degree of misperception in both job selection and resource allocation scenarios. The parameters which influence the degree of misperception are also extensively investigated. The results presented in this paper are of significant benefit to scheduling approaches that take into account predictive data; the results are also of importance to the application of these scheduling techniques to real-world high-performance systems.

AB - This paper investigates the underlying impact of predictive inaccuracies on execution scheduling, with particular reference to execution time predictions. This study is conducted from two perspectives: from that of job selection and from that of resource allocation, both of which are fundamental components in execution scheduling. A new performance metric, termed the degree of misperception, is introduced to express the probability that the predicted execution times of jobs display different ordering characteristics from their real execution times due to inaccurate prediction. Specific formulae are developed to calculate the degree of misperception in both job selection and resource allocation scenarios. The parameters which influence the degree of misperception are also extensively investigated. The results presented in this paper are of significant benefit to scheduling approaches that take into account predictive data; the results are also of importance to the application of these scheduling techniques to real-world high-performance systems.

KW - Execution time

KW - Job selection

KW - Performance evaluation

KW - Performance prediction

KW - Resource allocation

KW - Scheduling

UR - http://www.scopus.com/inward/record.url?scp=14544275056&partnerID=8YFLogxK

U2 - 10.1016/j.peva.2004.10.015

DO - 10.1016/j.peva.2004.10.015

M3 - Article

AN - SCOPUS:14544275056

VL - 60

SP - 127

EP - 139

JO - Performance Evaluation

JF - Performance Evaluation

SN - 0166-5316

IS - 1-4

ER -