• Journal of the Korean Statistical Society
• /
• v.32 no.4
• /
• pp.359-371
• /
• 2003

We consider the probability that the total population of a stable Jackson network reaches a given large value. By using the fluid limit of the reversed network, we derive new upper and lower bounds on this probability, which are sharper than those in Glasserman and Kou (1995). In particular, the improved lower bound is useful for analyzing the performance of an importance sampling estimator for the overflow probability in Jackson tandem networks. Bounds on the expected time to overflow are also obtained.

• Communications for Statistical Applications and Methods
• /
• v.8 no.1
• /
• pp.257-269
• /
• 2001

The simulation is used to estimate an overflow probability in a stable parallel network with coupled inputs. Since the general simulation needs extremely many trials to obtain such a small probability, the fast simulation is proposed to reduce trials instead. By using the Cramer’s theorem, we first obtain an optimally changed measure under which the variance of the estimator is minimized. Then, we use it to derive an importance sampling estimator of the overflow probability which enables us to perform the fast simulation.

• Proceedings of the Korean Statistical Society Conference
• /
• 2000.11a
• /
• pp.109-113
• /
• 2000

We consider the probability that the total population of a Jackson network exceeds a given large value. By using the relation to the stationary distribution, we derive upper and lower bounds on this probability. These bounds imply the stronger logarithmic limit than that in Glasserman and Kou(1995) when several nodes have the same maximal load.

• Journal of the Korean Society of Safety
• /
• v.35 no.5
• /
• pp.30-38
• /
• 2020

In order to construct a dam, the diversion facility such as cofferdam and a diversion tunnel should be installed in advance. And size of a cofferdam depends on type of a main dam. According to the Korea Dam Design Standard, if the main dam is a concrete dam, design flood of the cofferdam is 1~2 years flood frequency. This means that overflow of the cofferdam occurs one time for 1 or 2 years, therefore, stability of the cofferdam should be secured against any overflow problem. In this study, failure probability analysis for the concrete cofferdam is performed considering the overflow. First of all, limit state function of the concrete cofferdam is defined for overturning, sliding and base pressure, and upstream water levels are set as El. 501 m, El. 503 m, El. 505 m, El. 507 m. Also, after literature investigation research, probabilistic characteristics of various random variables are determined, the failure probability of the concrete cofferdam is calculated using the Monte Carlo Simulation. As a result of the analysis, when the upstream water level rises, it means overflow, the failure probability increases rapidly. In particular, the failure probability is largest in case of flood loading condition. It is considered that the high upstream water level causes increase of the upstream water pressure and the uplift pressure on the foundation. In addition, among the overturning, the sliding and the base pressure, the overturing is the major cause for the cofferdam failure considering the overflow.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.3
• /
• pp.404-410
• /
• 1999

A scheme of more exact overflow probability analysis is proposed for traffic regulated by dual leaky bucket. To each regulated traffic stream is allocated bandwidth and buffer independent of other traffic stream and overflow occurs when total bandwidth or buffer allocated to each traffic exceed link capacity or physical buffer size. Ratio of buffer and bandwidth allocated to each traffic stream is assumed to be constant, and this ratio is larger than the ratio of physical buffer and bandwidth due to buffer sharing effect. Numerical experiments show that this sharing effect have significant influence on overflow probability and effective bandwidth.

• Communications for Statistical Applications and Methods
• /
• v.20 no.5
• /
• pp.377-385
• /
• 2013

We consider a compound Poisson risk model in which the premium rate changes when the surplus exceeds a threshold. The explicit form of the ruin probability for the risk model is obtained by deriving and using the overflow probability of the workload process in the corresponding M/G/1 queueing model.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.12 no.1
• /
• pp.33-39
• /
• 2008

We consider a queueing system fed by a superposition of multiple discrete autoregressive processes of order 1, and propose an approximation method to estimate the overflow probability of the system. Numerical examples are provided to validate the proposed method.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.4
• /
• pp.171-180
• /
• 2004

CDP(handoff Call Dropping Probability) and CBP(new Call Blocking Probability) have been used as two important call level QoS parameters in cellular mobile communications. But, many methods to reduce CDP without considering CBP have been studied, and hand-off call priority scheme has been introduced. But the use of hand-off call priority scheme increases CBP and decreases channel utilization rate depending on the number of reserved channel for priority. In this paper, we propose a CAC(Call Admission Control) algorithm with overflow and preemption to solve the problem caused by considering CDP and CBP in calculation of the number of channel reserved. The problem is the increase of CDP as the traffic load increases. In our CAC algorithm, hand-off call is permitted to use(overflow) unreserved and unused channel if there is no reserved and unused channel, and new call is permitted to use(preemption) the channel overflowed by hand-off call if there is no unreserved and unused channel. This mechanism of calculation of the number of reserved channel and CAC algorithm is expected to increase channel utilization rate, and can be applied to media-based QoS provision in cellular mobile communications.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.4
• /
• pp.1045-1056
• /
• 2007

We consider M/M/1 feedback queues with multi-class customers. We assume that different classes of customers have different arrival rates, service rates and feedback probabilities. Using the h-transforms of McDonald(999) we derive an importance sampling estimator for an overflow probability that the total number of customers in the system reaches a high level before emptying.

• Communications for Statistical Applications and Methods
• /
• v.18 no.4
• /
• pp.433-443
• /
• 2011

We consider a compound Poisson risk model in which the premiums may depend on the state of the surplus process. By using the overflow probability of the workload process in the corresponding M/G/1 queueing model, we obtain the probability that the ruin occurs before the surplus reaches a given large value in the risk model. We also examplify the ruin probability in case of exponential claims.