Considering Bayesian Inference for Transient GI/G/1 Queuing Systems
|
Reza Salehi Rad, Asieh Abbasi * |
|
|
Abstract: (3592 Views) |
In this article, we are going to interpret one of the queueing systems with a single server that has general and unknown distribution for the service and interarrival time using Bayesian view point.
These General distributions may be well approximated by family of Mixed General Erlang distribution (MGE). This distribution is reparametrized such that it is possible to define a non-informative prior which allows using the MCMC method for estimating the parameters of models.
Using the results of simulating parameters, we can estimate interesting measures that are based on recent results for known parameters in GI/G/1 frequently implemented queueing systems. At the end, we illustrate our approach for analyzing GI/G/1 systems with data from a bank. |
|
Keywords: GI/G/1 queueing system, Bayesian inference, mixed general Erlang distribution, transient analysis, Monte Carlo Markov chain (MCMC). |
|
Full-Text [PDF 470 kb]
(789 Downloads)
|
Type of Study: Research |
Subject:
General Received: 2010/02/3 | Accepted: 2011/04/19 | Published: 2015/12/30
|
|
|
|