OASIcs.WCET.2010.44.pdf
- Filesize: 362 kB
- 10 pages
Document
Realism in Statistical Analysis of Worst Case Execution Times
Authors
-
Part of:
Volume:
10th International Workshop on Worst-Case Execution Time Analysis (WCET 2010)
Series: Open Access Series in Informatics (OASIcs)
Conference: Workshop on Worst-Case Execution Time Analysis (WCET) - License:
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license
- Publication Date: 2010-11-26
Cite As Get BibTex
David Griffin and Alan Burns. Realism in Statistical Analysis of Worst Case Execution Times. In 10th International Workshop on Worst-Case Execution Time Analysis (WCET 2010). Open Access Series in Informatics (OASIcs), Volume 15, pp. 44-53, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2010)
https://doi.org/10.4230/OASIcs.WCET.2010.44
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.
Subject Classification
Keywords
- WCET
- Extreme value statistics
- Gumbel distribution
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads