In this paper, we discuss a Monte Carlo sampling based method for propagating the epistemic uncertainty in model parameters, through the system availability model. We also outline methods to compute the number of samples needed to obtain a desired confidence interval for various scenarios. We illustrate this method with a real system example and discuss the results obtained. While our example discusses confidence interval for system availability, this method can be directly applied to compute uncertainty for other dependability, performance and perform ability measures, computed by solving stochastic analytic models. We also emphasize the fact that no simulation is carried out in our method but a repeated sampling is performed over the parameter space followed by the execution of the analytic model with the final phase being the statistical analysis of the output vector.
Description
IEEE Xplore Abstract - Uncertainty Propagation in Analytic Availability Models
%0 Conference Paper
%1 devaraj2010uncertainty
%A Devaraj, A
%A Mishra, K.
%A Trivedi, K.S.
%B Reliable Distributed Systems, 2010 29th IEEE Symposium on
%D 2010
%K availability propagation uncertainty
%P 121-130
%R 10.1109/SRDS.2010.22
%T Uncertainty Propagation in Analytic Availability Models
%U http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5623384
%X In this paper, we discuss a Monte Carlo sampling based method for propagating the epistemic uncertainty in model parameters, through the system availability model. We also outline methods to compute the number of samples needed to obtain a desired confidence interval for various scenarios. We illustrate this method with a real system example and discuss the results obtained. While our example discusses confidence interval for system availability, this method can be directly applied to compute uncertainty for other dependability, performance and perform ability measures, computed by solving stochastic analytic models. We also emphasize the fact that no simulation is carried out in our method but a repeated sampling is performed over the parameter space followed by the execution of the analytic model with the final phase being the statistical analysis of the output vector.
@inproceedings{devaraj2010uncertainty,
abstract = {In this paper, we discuss a Monte Carlo sampling based method for propagating the epistemic uncertainty in model parameters, through the system availability model. We also outline methods to compute the number of samples needed to obtain a desired confidence interval for various scenarios. We illustrate this method with a real system example and discuss the results obtained. While our example discusses confidence interval for system availability, this method can be directly applied to compute uncertainty for other dependability, performance and perform ability measures, computed by solving stochastic analytic models. We also emphasize the fact that no simulation is carried out in our method but a repeated sampling is performed over the parameter space followed by the execution of the analytic model with the final phase being the statistical analysis of the output vector.},
added-at = {2014-09-11T09:51:53.000+0200},
author = {Devaraj, A and Mishra, K. and Trivedi, K.S.},
biburl = {https://www.bibsonomy.org/bibtex/2fc7c85abbd003a3463226f605827899a/avail_map_stud},
booktitle = {Reliable Distributed Systems, 2010 29th IEEE Symposium on},
description = {IEEE Xplore Abstract - Uncertainty Propagation in Analytic Availability Models},
doi = {10.1109/SRDS.2010.22},
interhash = {e4b48de051928e8e89eff0916681bb4f},
intrahash = {fc7c85abbd003a3463226f605827899a},
issn = {1060-9857},
keywords = {availability propagation uncertainty},
month = oct,
pages = {121-130},
timestamp = {2014-09-11T09:51:53.000+0200},
title = {Uncertainty Propagation in Analytic Availability Models},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5623384},
year = 2010
}