• 한국정보과학회논문지:정보통신
• /
• 제28권4호
• /
• pp.517-526
• /
• 2001

현재의 인터넷 라우터는 Drop tail 방법으로 패킷을 처리한다. 따라서 네트워크 트래픽의 지수적인 증가로 인한 혼잡상황 때문에 많은 패킷이 손실 될 수 있다. 이러한 문제를 해결하기 위해 IETF(Internet Engineering Task Force)에서는 RED(Random Early Detection)와 같은 능동적인 큐 관리 알고리즘을 제시하였다. 이러한 알고리즘은 라우터나 게이트웨이에서 발생할 수 있는 네트워크 혼잡상황을 개선하여 전체적인 패킷 손실을 줄여 줄 수 있다. 그러나 RED 알고리즘의 경우 큐 크기의 변화 정보로 혼잡상황을 판단하고 제어하기 때문에 동적으로 변화하는 현재의 인터넷 트래픽 대한 혼잡상황 제어에 있어서 개선의 필요성이 있다. 본 논문에서는 이러한 RED 알고리즘의 문제를 보완하기 위해서 기존의 RED 알고리즘을 개선한 MRED(Modified Random Early Detection) 알고리즘을 제안했다. 제안한 알고리즘은 간단하게 폐기(drop) 확률을 구하는 RED에 비하여 휴리스틱 (heuristic)한 방법을 적용하여 보다 동적으로 폐기 확률 값을 계산한다. MRED 알고리즘의 성능을 검증하기 위해서 실힘을 통하여 기존의 큐 관리 방법과 성능을 비교하였고 리눅스 커널에 MRED를 구현하여 성능을 분석하였다.

• ETRI Journal
• /
• 제25권1호
• /
• pp.34-40
• /
• 2003

This paper considers a TMN-based management system for the management of public ATM switching networks using a four-level hierarchical structure consisting of one network management system, several element management systems, and several agent-ATM switch pairs. Using Jackson's queuing model, we analyze the effects of one TMN command on the performance of the component ATM switch in processing local calls. The TMN command considered is the permanent virtual call connection. We analyze four performance measures of ATM switches- utilization, mean queue length and mean waiting time for the processor directly interfacing with the subscriber lines and trunks, and the call setup delay of the ATM switch- and compare the results with those from Jackson's queuing model.

• 한국경영과학회지
• /
• 제18권3호
• /
• pp.179-186
• /
• 1993

We derive the arbitrary time point system size distribution of M/ $G^{B}$1 queue in which late arrivals are not allowed to join the on-going service. The distribution is given by P(z) = $P_{4}$(z) $S^{*}$ (.lambda.-.lambda.z) where $P_{4}$ (z) is the probability generating function of the queue size and $S^{*}$(.theta.) is the Laplace-Stieltjes transform of the service time distribution function. We also derive the distribution of the service siez at arbitrary point of time. time.

• Industrial Engineering and Management Systems
• /
• 제7권2호
• /
• pp.143-149
• /
• 2008

There have been some approximation analysis methods for a GI/G/1 queueing system. As one of them, an approximation technique for the steady-state probability in the GI/G/1 queueing system based on the iteration numerical calculation has been proposed. As another one, an approximation formula of the average queue length in the GI/G/1 queueing system by using the diffusion approximation or the heuristics extended diffusion approximation has been developed. In this article, an approximation technique in order to analyze the GI/G/1 queueing system is considered and then the formulae of both the steady-state probability and the average queue length in the GI/G/1 queueing system are proposed. Through some numerical examples by the proposed technique, the existing approximation methods, and the Monte Carlo simulation, the effectiveness of the proposed approximation technique is verified.

• 한국멀티미디어학회논문지
• /
• 제18권12호
• /
• pp.1475-1482
• /
• 2015

In network routers, buffers are used to resolve congestion and reduce packet loss rate whenever congestion occurs at bottleneck link. Most of the existing methods to manage such buffers focus only on queue-length-based control as one loop which have some issues of low link utilization and system stability. In this paper, we propose a novel framework which exploits two-loop control method, e.g. queue-length and congestion window size, combined with optimal margin method to facilitate parameter choices. Simulation results in ns-2 demonstrate that bottleneck link performance can be improved with higher link utilization (85%) and shorter queue length (22%) than the current deployed scheme in commercial routers (RED and DropTail).

• 제어로봇시스템학회논문지
• /
• 제12권6호
• /
• pp.614-620
• /
• 2006

Today the automobile has been changed from a mechanical system to an electronic control system fly the development of the electronic technology. In the automobile body, most of these electronic control devices are networked and managed fully by the CAN protocol. But, when a network system is overloaded, unexpected transmission delay for relative low priority objects occurs due to the static priority definition of the CAN protocol. To resolve this problem, this paper proposes a dynamic precedence queue mechanism that creates a queue for the low priority object and its relevant objects to be transmitted, which becomes urgent in an overloaded network system to keep the maximum allowable time delay. For the generated queue, the highest priority is assigned to transmit the queued objects within the shortest time. The mechanism is implemented in the logical link layer of CAN, which does not require any modification of the old CAN hardware. Effectiveness of the proposed mechanism is verified by the real experiments with an automobile network system.

• 한국인터넷방송통신학회논문지
• /
• 제18권5호
• /
• pp.141-146
• /
• 2018

본 논문에서는 스마트폰으로 번호표 발행기와 은행의 서버 컴퓨터를 연동하여 효율적인 고객관리를 위한 시스템을 제안한다. 본 논문에서 제안한 배경은 다음과 같다. 이전부터 은행에서 사용하는 고객관리 시스템은 일반 사용자를 대상으로 사용하고 있다. 하지만 스마트폰의 발전으로 온라인 이용자가 증가함과 동시에 은행 지점의 수는 감소하여, 오프라인에서 은행을 직접 이용하였을 때 장시간의 대기시간이 발생한다. 또한 고객의 비효율적인 시간 손실이 발생함에 따라 고객 서비스에도 문제가 생기고 있다. 본 논문은 이러한 고객관리 문제에서 발생하는 고객 서비스를 개선하기 위하여 스마트폰과 오프라인에서 사용하고 있는 번호표 발행기를 활용하여 고객 경우의 수에 따른 큐 관리 시스템을 제안하였다.

• 한국경영과학회지
• /
• 제26권4호
• /
• pp.39-45
• /
• 2001

Maximum and minimum of rendom variables are frequently encountered in the stochastic modelling for various OR problems. We summarize and extend characteristics of maximum and minimum, emphasizing the case in which random variables are independent and all of them except one are distributed exponential. As an application, we derive a transform-free expression for the M/G/1 queue length distribution.

• 한국경영과학회지
• /
• 제22권2호
• /
• pp.31-44
• /
• 1997

This paper presents an approximate analytical model to estimate the mean packet walting times at the stations in the IEEE 802, 6 subnetwork of a metropolitan area network. Each station is modeled as a two queue single server system, which serves data packets and requests from downstream stations according to the DQDB protocol. The model estimates the mean waiting time of the requests and in turn, using the discrete time work conservation law, estimates the mean waiting time for packets. Simulation experiments shows that the model accurately works even under very high traffic loads.

• 한국경영과학회지
• /
• 제15권1호
• /
• pp.117-133
• /
• 1990

This paper is concerned with determining a minisum location with jockeying for a server on a probabilistic network in which each customer type enters the network system permitting with jockeying through a specified node and a nonpreemptive service policy is in effect. An algorithm to locate a single Fixed Priority Queue Median with Jockeying (FPQMJ) on acyclic networks is developed by using the Generalized Benders' Decomposition technique. The results are then extended to a general network.