• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.802-810
• /
• 1997

In this paper, the performance of direce mapping caches, 2_, 4_, 8_, .., 4096_way way set associative caches, and fully assiciative caches are analyized by trace simulation for verivying their effectiveness.In general, it is well known that as n, the number of main memory lines to be stored into one cache line number in direct mapping cache, increases, the performance of the cache memory should get higher linearly.According to our analysis, however, it is not true on all the cache organizations.It is shown that as n increases, miss ratios get lower only when the small cache(less than 256K) using large line size is used.It is also shown that fully associative mapping achieves high performance only when small size cache using large line size ia used.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.5
• /
• pp.962-966
• /
• 2009

In this paper, N-way resistance power divider is described for wideband frequency characteristic. For this, we derived in design equation of a N-way resistance power divider using 3-way resistance power divider. We designed 8-way resistance power divider that can divide same power by 7 output and measurement result of fabricated resistance power divider is observed to prove the validity of derived design equation. Fabricated resistance power divider shown equal power division ratio and reflection loss displayed excellent characteristic by about -25dB in broadband from DC to 3GHz.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.8
• /
• pp.390-398
• /
• 2001

인터넷을 이용한 서비스와 산업이 급속도로 발전하면서 인터넷 서비스를 위한 효율적이며 확장성이 있는 고가용성 시스템이 매우 중요한 요소로 인식되고 있다. 인터넷 서비스를 위한 고가용성 시스템은 컴퓨터들이 쉬지 않고 서비스를 제공할 수 있는 active-active 형태로 구성되어야 하며, 확장성을 위해서 N개의 컴퓨터가 연결되어 클러스터를 구성하는 N-way 방식을 지원하여야 한다. 본 논문에서는 N개의 컴퓨터들이 클러스터로 연결된 N-way에서 active-active 형태의 구성을 위한 알고리즘을 제시하고, 이를 바탕으로 구현된 고가용성 시스템인 Diehard를 소개한다. Diehard는 인터넷 서비스의 특성을 고려해서 소프트웨어 SPOF를 모니터링하고, 부분적인 서비스 중단에 대한 다양한 복구 정책 등을 지원하도록 설계 및 구현되었다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.9
• /
• pp.445-453
• /
• 2003

As cluster systems used for high performance computing consist of large number of running servers, one has to solve the low availability problems occurred by the high chance of the server failures. To handle the problems, it is necessary to have the precise definition of available performance of cluster systems that represents availability and performability of the systems simultaneously. Previous research results that mention availability issues lack for concerning system performance such as waiting time and response time in their availability definition. In this paper, we propose a new availability metric for (n, k)-way cluster systems which compose of n primary servers and k backup servers. With the metric, the change of system performance according to arrival rates is captured and the waiting time of a request can be kept below to a certain level. Using various system operating parameters, we calculate availability and downtime of cluster systems along with waiting tine deadline.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10c
• /
• pp.838-840
• /
• 2001

인터넷 서비스를 위한 시스템은 지속적인 서비스가 이루어져야 하므로, 보다 효율적으로 중단 없는 인터넷 서비스의 확장성을 제공하기 위한 고가용성 시스템의 필요성이 증가하고 있다. 기존에 많은 연구가 이루어진 Active-Active형태의 클러스터 시스템은 단순히 두 대의 시스템만으로 운용되기 때문에 확장이 용이하지 못하다. 그래서 단순하게 시스템의 증가만으로 클러스터를 확장할 수 있는 N-way 방식의 클러스터를 지원하는 방식이 필요하게 된다. 본 논문은 이러한 확장을 고려하여 소프트웨어적으로 N개의 시스템을 클러스터로 구축하기 위해 개발된 알고리즘을 제시한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.123-126
• /
• 1995

Characteristics of control system design using Universal Learning Network (U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system in learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust control considered here is defined as follows. Even though initial values of node outputs change from those in learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation. In order to realize such robust control, a new term concerning the variation is added to a usual criterion function. And parameter variables are adjusted so as to minimize the above mentioned criterion function using the second order derivatives of criterion function with respect to the parameters. Finally it is shown that the controller constricted by the proposed method works in an effective way through a simulation study of a nonlinear crane system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.4
• /
• pp.378-386
• /
• 2013

In this paper, we propose a multi-way relaying system, in which N communicating nodes interchange their information one another by the help of a multiple-antenna non-regenerative relay station (RS). While the conventional multi-way relaying requires 2N transmission phases to complete the data exchange, the proposed system completes the mission with N phases composed of one multiple access phase and N-1 broadcast phases. For effective broadcast transmission, the proposed system pairs users for signal transmission with a new RS beamforming matrix not to interfere with the nodes of different pairs and a self-interference canceler at each node. The performance evaluation in terms of the average sum rate shows that the proposed system outperforms the conventional one with more significant gain when the number of RS antennas is comparable to the number of communicating nodes. The proposed schemes can be applicable to marine communications where the ships need to share their information with extended coverage.

• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.6 no.1
• /
• pp.28-36
• /
• 1995

In this paper, a design method of multiple n-way low loss power divider for x-band is propossed. To decrease loss, only two-stages of transmission lines are used with isolation resistors for match. Ex- perimental results for 3-way and 4-way power dividers have the divided power of 5.54~6.17dB and 6.76~7.37 dB, the return loss of more than 17dB and 12dB, and the isolation of more than 18dB and 10dB at center frequency, respectively, The measured results show good agreement with the theoretical analysis.

• ETRI Journal
• /
• v.16 no.1
• /
• pp.59-72
• /
• 1994

In this paper, a new N-way hybrid power combiner for improving the graceful degradation performance has been proposed. The proposed combiner has been configured with two dummy transmission lines per each section, where each dummy transmission line has a different characteristic impedance, of the standard combiner. Under this proposed configuration, a detailed theoretical analysis has been performed to show the general function of a power combiner. When any M amplifiers among N identical amplifiers are suffering the failure mode in a power combining circuit or system, the graceful degradation performance has been improved due to the separation of a transmission line and an internal resistor in every failed section from the proposed combiner by simultaneously operating two shorting devices. Simulation results for all the items which can be measured from all the items which can be measured from the proposed combiner with an eight-way configuration have been presented.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.779-782
• /
• 2014

맵리듀스(MapReduce)는 대용량 데이터의 병렬 처리에 사용되는 프로그래밍 모델이다. 조인(join)은 둘 이상의 테이블에서 동일한 애트리뷰트 값을 가지는 레코드들을 결합하는 연산으로, 데이터베이스 분야에서 가장 중요한 연산 중 하나이다. 본 논문은 맵리듀스를 이용하여 다중 조인(multi-way)을 효율적으로 처리하는 방법을 제안한다. n개 테이블의 다중 조인을 처리하기 위해 기존 방법은 2-way 조인을 수행하는 맵리듀스 잡을 (n-1)번 수행하거나, 레코드들을 중복시켜 n개 테이블의 조인을 1 개의 맵리듀스 잡으로 한 번에 처리한다. 하지만 전자는 맵리듀스 잡을 (n-1)번 수행해야 하며, 후자는 레코드들을 상당히 많이 중복시켜야 한다는 단점이 있다. 본 논문은 레코드를 전혀 중복시키지 않고도 ${\lceil}{\log}_2n{\rceil}$개의 맵리듀스 잡만으로 다중 조인을 효율적으로 처리하는 방법을 제안한다. 실험을 통해 제안 방법은 기존 방법에 대해 다중 조인을 더 빠르게 처리함을 보인다.