• Journal of the Korean Statistical Society
• /
• v.33 no.3
• /
• pp.283-298
• /
• 2004

We present a trial solution approach to GI/M/l queues with generalized vacations. Specific types of generalized vacations we consider are N -policy and a combination of N-policy and exponential multiple vacations. Discussions about how to find trial solutions are given.

• Journal of Korean Institute of Industrial Engineers
• /
• v.17 no.2
• /
• pp.107-113
• /
• 1991

This article develops a control model for an open queueing network in terms of both the input and the output processes with stochastic intensities. The input and the output intensities are subject to some capacity limits and optimum control is characterized by a threshold type with a finite upper barrier. A discounted profit is used as a decision criteria, which is revenue minus operating and holding cost.

• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.4
• /
• pp.137-146
• /
• 1993

We consider single server feedback queueing systems with priorities. In the model, there are J stations and job classes. Jobs of class i arrive at station i according to a Poisson process, and have a general service time distribution. We derive the generating functions of the number of jobs at each station just after a busy period and the formula for the mean sojourn time that a specific tagged job spends at station j from its arrival to departure from the system.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1999.04a
• /
• pp.1-5
• /
• 1999

An ATM switch is the basic component of an ATM network, and its functioning is to switch incoming cells arriving at an input port to the output port associated with an appropriate virtual path. In case of an ATM switch with buffer sharing scheme, the performance analysis is very difficult due to the interactions between the address queues. In this paper, the influences of the degree of traffic burstiness and some traffic routing properties are investigated by using the simulation. Also, some cell access strategies including priority access and cell dropping are compared in terms of cell loss probability.

• Journal of Korean Institute of Industrial Engineers
• /
• v.14 no.2
• /
• pp.1-10
• /
• 1988

We consider a vacation system in which the server takes two different types of vacations alternately. We obtain the server idle probability and derive the system size distribution and the waiting time distribution by defining supplementary variables. We show that the decomposition property works for these mixed-vacation queues. We also propose a method directly to obtain the waiting time distribution without resorting to the system equations. The T-policy is revisited and is shown that the cost is minimized when the length of vacations are the same.

• Journal of Korean Institute of Industrial Engineers
• /
• v.16 no.1
• /
• pp.107-114
• /
• 1990

A queueing system with compound Poisson arrival and server vacation is analyzed by including supplementary variables. We consider a vacation system in which the server leaves for a vacation as soon as the system empties. When he returns, if no customer is waiting for service, he waits until a group of customers arrive and then begins to serve. We obtain the system size distribution and the waiting time distribution. Additional performance measures will be also considered.

• Journal of Korean Institute of Industrial Engineers
• /
• v.6 no.1
• /
• pp.1-7
• /
• 1980

An exact solution technique for M/M/s multi-server demanding queue is introduced, and a general form of the curves representing service rates of the system is presented. As the number of customers in the system increases, the service rate is shown to increase initially, then decrease, and finally converge to a certain value. It is also shown that this phenomenon persists regardless of the numbers of servers and customer types.

• Journal of the Korea Society for Simulation
• /
• v.1 no.1
• /
• pp.31-36
• /
• 1992

To estimate the probability of long delay in a queuing system using discrete-event simulation is studied. We contrast the coverage, half-width, and stability of confidence intervals constructed using two methods: batch means and new resampling technique; binary bootstrap. The binary bootstrap is an extension of the conventional bootstrap that resamples runs rather than data values. Empirical comparisons using known results for the M/M/1 and D/M/10 queues show the binary bootstrap superior to batch means for this problem.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1992.10a
• /
• pp.13-13
• /
• 1992

To estimate the probability of long delay in a queuing system using discrete-event simulation studied. We contrast the coverage, half-width, and stability of confidence intervals constructed using two methods: batch means and new resampling technique; binary bootstrap. The binary bootstrap is an extension of the conventional bootstrap that resamples runs rather than data values. Empirical comparisons using known results for the M/M/1 and D/M/10 queues show the binary bootstrap superior to batch means for this problem.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.26 no.1
• /
• pp.1-22
• /
• 2022

A tandem queue that consists of nodes with buffers of finite capacity and general blocking scheme is considered. The service time distribution of each node is exponential whose rate depends on the state of the node. The blocking scheme at a node may be different from that of other nodes. An approximation method for the system based on decomposition method is presented. The effectiveness of the method is investigated numerically.