• Journal of Communications and Networks
• /
• 제9권3호
• /
• pp.330-341
• /
• 2007

This work analyzes the performance of the parallel packet switch (PPS) with a sliding window (SW) method. The PPS involves numerous packet switches that operate independently and in parallel. The conventional PPS dispatch algorithm adopts a round robin (RR) method. The class of PPS is characterized by deployment of parallel low-speed switches whose all memory buffers run more slowly than the external line rate. In this work, a novel SW packet switching method for PPS, called SW-PPS, is proposed. The SW-PPS employs memory space more effectively than the existing PPS using RR algorithm. Under identical Bernoulli and bursty data traffic, the SW-PPS provided significantly improved performance when compared to PPS with RR method. Moreover, this investigation presents a novel mathematical analytical model to evaluate the performance of the PPS using RR and SW method. Under various operating conditions, our proposed model and analysis successfully exhibit these performance characteristics including throughput, cell delay, and cell drop rate.

• 대한수학회논문집
• /
• 제10권3호
• /
• pp.735-750
• /
• 1995

We present a domain decomposition algorithm for solving large sparse linear systems of equations arising from queuing networks. Such techniques are attractive since the problems in subdomains can be solved independently by parallel processors. Many of the methods proposed so far use some form of the preconditioned conjugate gradient method to deal with one large interface problem between subdomains. However, in this paper, we propose a "nested" domain decomposition method where the subsystems governing the interfaces are small enough so that they are easily solvable by direct methods on machines with many parallel processors. Convergence of the algorithms is also shown.lso shown.

• International Journal of Contents
• /
• 제1권1호
• /
• pp.40-44
• /
• 2005

This paper introduces region partitioning method of non-perfect nested loops with non-uniform dependences. This kind of loop normally can't be parallelized by existing parallelizing compilers and transformations. Even when parallelized in rare instances, the performance is very poor. Based on the Convex Hull theory which has adequate information to handle non-uniform dependences, this paper proposes an enhanced region partitioning method which divides the iteration space into minimum parallel regions where all the iterations inside each parallel region can be executed in parallel by using variable renaming after copying.

• 전기학회논문지
• /
• 제57권1호
• /
• pp.40-45
• /
• 2008

This paper presents an optimal design of a permanent magnet actuator(PMA) using a parallel genetic algorithm. Dynamic characteristics of permanent magnet actuator model are analyzed by coupled electromagnetic-mechanical finite element method. Dynamic characteristics of PMA such as holding force, operating time, and peak current are obtained by no load test and compared with the analyzed results by coupled finite element method. The permanent magnet actuator model is optimized using a parallel genetic algorithm. Some design parameters of vertical length of permanent magnet, horizontal length of plunger, and depth of permanent magnet actuator are predefined for an optimal design of permanent magnet actuator model. Furthermore dynamic characteristics of the optimized permanent magnet actuator model are analyzed by coupled finite element method. A displacement of plunger, flowing current of the coil, force of plunger, and velocity of plunger of the optimized permanent magnet actuator model are compared with the results of a primary permanent magnet actuator model.

• Journal of Mechanical Science and Technology
• /
• 제16권5호
• /
• pp.609-618
• /
• 2002

In practical designs, most of the multidisciplinary problems have a large-size and complicate design system. Since multidisciplinary problems have hundreds of analyses and thousands of variables, the grouping of analyses and the order of the analyses in the group affect the speed of the total design cycle. Therefore, it is very important to reorder and regroup the original design processes in order to minimize the total computational cost by decomposing large multidisciplinary problems into several multidisciplinary analysis subsystems (MDASS) and by processing them in parallel. In this study, a new decomposition method is proposed for parallel processing of multidisciplinary design optimization, such as collaborative optimization (CO) and individual discipline feasible (IDF) method. Numerical results for two example problems are presented to show the feasibility of the proposed method.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2003년도 춘계전력전자학술대회 논문집(2)
• /
• pp.692-695
• /
• 2003

Generally, photovoltaic system is composed with several solar cell modules. For increasing power of photovoltaic systems, serial and parallel connection needed. A Desirable characteristic of a parallel supply system is that individual converters share the load current equally and stably. The current sharing(CS) can be implemented using two approaches. The first one, known as a droop method, relies on the high output impedance of each converter. and The second approach, known as active current-sharing techniques. In this paper, using droop method at parallel connection with it's convenience and simplicity.

• 전력전자학회논문지
• /
• 제5권4호
• /
• pp.409-416
• /
• 2000

시스템 특성상 fault tolerant system을 위해 두개의 컨버티를 1개의 전류센서를 사용하여 영상변류기 동적 방식으토 병렬 운전하는 경우 컨버터에 고자이 발생하면 영상변류기 출력은 두 컨버터 공급 전류 차이이므로, 어떤 컨버터에서 고장이 발생하였는지 고정 탐지 및 분리가 곤란히였다. 본 논문에사는 fault tolerant system를 위해 2 개의 컨버터를 병렬 운전하는 경우 캔버터의 고장 탐지 및 분리를 위한 방안올 제시하고 실험을 통하여 제안한 방법의 타당성을 확인하였다.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제53권4호
• /
• pp.255-261
• /
• 2004

This paper presents an improved droop method which minimizes the voltage droop of a parallel-connected power supply Conventionally, the droop method has been used to achieve a simple structure and no-interconnections among power sources. However, it has a trade-off between output voltage regulation and load sharing accuracy In this paper, the droop is minimized with a current and droop gain control using steady-stage estimation. The proposed method can achieve both good voltage regulation and good load sharing. A design example of two 10㎸, 100㎃ parallel modules is made and tested to verify the proposed current-sharing method.

• 한국산업융합학회 논문집
• /
• 제26권6_2호
• /
• pp.1097-1108
• /
• 2023

Recently, demand for technology for energy economy and stable supply is increasing due to the increase in power demand of loads. The amount of DC power generation using new and renewable energy is noticeably increasing, and the use of DC power supplies is also increasing due to the increase in electric vehicles and digital loads. During parallel operation to increase the capacity of the power converter, the module bus method or the method using Can communication and serial communication has significant difficulties in smooth operation due to communication time delay for information sharing. Synchronization of information sharing of each power converter is essential for smooth parallel operation, and minimization of communication time delay is urgently needed as a way to overcome this problem. In this paper, a new communication method using pulse width information is proposed as a communication method specialized for parallel operation of power converters to compensate for the disadvantage of communication transmission delay in the existing system. The proposed communication method has the advantage of being easily implemented using the PWM and Capture function of the microcomputer. In addition, the DC/DC converter for DC distribution was verified through simulation and experiment, and it has the advantage of easy capacity expansion when applied to parallel operation of various types of power converters as well as DC/DC converters.

• 한국지반환경공학회 논문집
• /
• 제25권4호
• /
• pp.13-20
• /
• 2024

본 논문에서는 유동체를 해석할 수 있는 수치해석기법 중 하나인 SPH(Smoothed Particle Hydrodynamics)의 병렬해석 알고리즘이 소개된다. 무요소법(meshless method)의 SPH는 연속체 거동을 입자기반으로 표현하기 때문에 컴퓨팅하는데 높은 자원을 요구한다. 그래서 병렬해석 알고리즘은 SPH 시뮬레이션에서 필수적으로 고려되어야 한다. 계산영역을 일정한 간격으로 분할시켜 독립적으로 해석하는 영역분할 알고리즘은 병렬해석 알고리즘 중에 가장 대표적인 방법이다. 그리고 그 중 Cartesian 좌표계의 영역분할 방법은 입자들의 좌표를 빠르고 편리하게 검색할 수 있는 장점이 있어, DEM(Discrete Element Method)이나 MD(Molecular Dynamics)에서 대중적으로 사용되고 있다. 그러나 SPH의 경우 입자들이 smoothing 길이 이내의 주위 입자 정보가 필요하기 때문에 분할 영역 간의 입자정보 공유가 중요하다. 그리고 이에 따른 CPU의 로드밸런스가 중요하다. 본 연구에서는 직교 영역분할의 크기를 동적으로 미소화 시켜 잉여 CPU가 발생하지 않도록 하는 높은 병렬효율성의 알고리즘이 제안되었다. 그리고 수치해석 모델을 통하여 효율성을 검증하였다. 유동체 모델에 대해 총 30 CPU까지 제안된 방법의 병렬효율성을 검토하였고, 28개의 물리적 코어 수까지 90%의 병렬효율성을 얻을 수 있었다.