License: Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license (CC BY-NC-ND 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.WCET.2010.44
URN: urn:nbn:de:0030-drops-28245
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2010/2824/
Griffin, David ;
Burns, Alan
Realism in Statistical Analysis of Worst Case Execution Times
Abstract
This paper considers the use of Extreme Value Theory (EVT) to model worst-case execution times. In particular it considers the sacrifice that statistical methods make in the realism of their models in order to provide generality and precision, and if the sacrifice of realism can impact the safety of the model. The Gumbel distribution is assessed in terms of its assumption of continuous behaviour and its need for independent and identically distributed data. To ensure that predictions made by EVT estimations are safe, additional restrictions on their use are proposed and justified.
BibTeX - Entry
@InProceedings{griffin_et_al:OASIcs:2010:2824,
author = {David Griffin and Alan Burns},
title = {{Realism in Statistical Analysis of Worst Case Execution Times}},
booktitle = {10th International Workshop on Worst-Case Execution Time Analysis (WCET 2010)},
pages = {44--53},
series = {OpenAccess Series in Informatics (OASIcs)},
ISBN = {978-3-939897-21-7},
ISSN = {2190-6807},
year = {2010},
volume = {15},
editor = {Bj{\"o}rn Lisper},
publisher = {Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
address = {Dagstuhl, Germany},
URL = {http://drops.dagstuhl.de/opus/volltexte/2010/2824},
URN = {urn:nbn:de:0030-drops-28245},
doi = {10.4230/OASIcs.WCET.2010.44},
note = {The printed version of the WCET'10 proceedings are published by OCG (www.ocg.at) - ISBN 978-3-85403-268-7},
annote = {Keywords: WCET, Extreme value statistics, Gumbel distribution}
}
Keywords: |
|
WCET, Extreme value statistics, Gumbel distribution |
Collection: |
|
10th International Workshop on Worst-Case Execution Time Analysis (WCET 2010) |
Issue Date: |
|
2010 |
Date of publication: |
|
26.11.2010 |