Academic Journals Database
Disseminating quality controlled scientific knowledge

Rare Events Prediction Using Importance Sampling in a Tandem Network

Author(s): Behrouz Safaiezadeh

Journal: International Journal of Computer Science and Network Solutions
ISSN 2345-3397

Volume: 1;
Issue: 2;
Start page: 1;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Importance Sampling | Rare Event | Jackson Network | Deadline | Performance

Importance sampling is a technique that is commonly used to speed up Monte Carlo simulation of rare events.Estimating probabilities associated to rare events has been a topic of great importance in queueing theory, and in appliedprobability at large. We analyze the performance of an importance sampling estimator for a rare event probability in aJackson network. The present paper carries out strict deadlines to a two-node Jackson network whose arrival and servicerates are modulated by an exogenous finite state Markov process. We derive a closed form solution for the probability ofmissing deadline. Then the results have employed in an importance sampling technique to estimate the probability oftotal population overflow which is a rare event. We have also shown that the probability of this rare event may beaffected by various deadline values.
Affiliate Program      Why do you need a reservation system?