• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.4
• /
• pp.88-95
• /
• 2013

A new droop control method which can be applied to 3-phase 4-wire uninterruptible power supply is proposed in this paper. The droop control method for parallel operation is very attractive one as UPS parallel operation can be carried out without any data communication devices provided among UPS systems connected, but it reportedly shows a PnP(plug-and-play) problem. A basic reason why a circulating current could flow among parallel-connected UPS systems is clearly investigated as well when droop-controlled-ups systems are operated in the manner of PnP. The proposed algorithm is deduced from the investigated result and is basically structured to keep a balanced frequency and balanced voltage profile against power variation. This paper shows that balanced parallel operation of droop control method can be obtained under unbalanced load as well as balanced load conditions when PnP operation is needed and load change occurs.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.8
• /
• pp.33-40
• /
• 2006

A parallel computing strategy for finite element(FE) processing is described and implemented in nonlinear explicit FE code and its parallel performances are evaluated. A self-made linux-cluster supercomputer with 520 CPUs is used as a bench mark test bed. It is observed that speed-up is increased almost idealy even up to 256 CPUs for a large scale model. A communication over head and its effect on the parallel performance is also examined. Parallel performance is compare with the commercial code and developed code shows superior performance as the number of CPUs used are increased.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.3
• /
• pp.236-242
• /
• 2004

In this paper, we propose an approach to parallelize a load balancing algorithm that was shown to be very effective in distributing workload for parallel computations. Load balancing algorithms are required in executing parallel program efficiently As a parallel computation model, we used dynamically growing tree structure that can be found in many application problems. The load balancing algorithm tries to balance the workload among processors while keeping the communication cost under certain limit. We show how the load balancing algorithm is effectively parallelized on mesh and hypercube interconnection networks, and analyzed the time complexity for each case to show that parallel algorithm actually reduced the various overhead.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.176-179
• /
• 2002

In recent years, an increasing amount of computer network research has focused on the problem of cluster system in order to achieve higher performance and lower cost. The load unbalance is the major defect that reduces performance of a cluster system that uses parallel program in a form of SPMD (Single Program Multiple Data). Also, the load unbalance is a problem of MPP (Massive Parallel Processors), and distributed system. The cluster system is a loosely-coupled distributed system, therefore, it has higher communication overhead than MPP. Dynamic load balancing can solve the load unbalance problem of cluster system and reduce its communication cost. The cluster systems considered in this paper consist of P heterogeneous nodes connected by a switch-based network. The master node can predict the average execution time of tasks for each slave node based on the information from the corresponding slave node. Then, the master node redistributes remaining tasks to each node considering the predicted execution time and the communication overhead for task migration. The proposed dynamic load balancing uses execution time prediction to optimize the task redistribution. The various performance factors such as node number, task number, and communication cost are considered to improve the performance of cluster system. From the simulation results, we verified the effectiveness of the proposed dynamic load balancing algorithm.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.18 no.6
• /
• pp.515-522
• /
• 2013

In this paper, a new PCS is proposed which is consisted of high boost dual converter and single phase half-bridge inverter. The proposed PCS is configured in parallel input / serial output, using two interleaved voltage doubler converter. Converter of the proposed PCS is distribute input current by configuring parallel input and reduced turn ratio of transformer by configuring serial output. Also, compositions of the inverter are composed of serial output capacitor of converter and half-bridge inverter. The dual converter and single phase half-bridge inverter is designed and characteristic of the new PCS is analysed. The system of the 1.5[kW] PCS is verified through an experimental about operation and stability.

• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.4 no.1
• /
• pp.28-37
• /
• 1993

The future Personal Communication Service(PCS) is the total personal information communication service to satisfy the importance of information in a highly information - oriented society. Compared with the conventional communication method, it is necessary to provide considerable intelligence to the commu- nication network in order to implement the PCS which guarantees the mobility of each individual. Consequen- tly, the PCS needs a fast large database system which stores the information of each individual. To achieve this goal, this paper presents the parallel implementation of deductive database systems as a main - memory database system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.138-144
• /
• 2010

Tachyon primary system which introduces recently is a high performance supercomputer that composed with AMD Barcelona nodes. In this paper, we will verify the performance and parallel scalability of TachyonIn by using multi-zone NAS Parallel Benchmark(NPB) which is one of a program with hybrid parallel method. To test performance of hybrid parallel execution, B and C classes of BT-MZ in NPB version 3.3 were used. And the parallel scalability test has finished with Tachyon's 1024 processes. It is the first time in Korea to get a result of hybrid parallel computing calculation using more than 1024 processes. Hybrid parallel method in high performance computing system with multi-core technology like Tachyon describes that it can be very efficient and useful parallel performance benchmarks.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.1-11
• /
• 2020

In this paper, we present a technique that executes MPI parallel programs, that are developed on processor-centric computer architecture, more efficiently on memory-centric computer architecture without program modification. The technique we present here improves performance by replacing low-speed data communication over the network of MPI library functions with high-speed data communication using the property called fast large shared memory of memory-centric computer architecture. The technique we present in the paper is implemented in two programs. The first program is a modified MPI library called MC-MPI-LIB that runs MPI parallel programs more efficiently on memory-centric computer architecture preserving the semantics of MPI library functions. The second program is a simulation program called MC-MPI-SIM that simulates the performance of memory-centric computer architecture on processor-centric computer architecture. We developed and tested the programs on distributed systems environment deployed on Docker based virtualization. We analyzed the performance of several MPI parallel programs and showed that we achieved better performance on memory-centric computer architecture. Especially we could see very high performance on the MPI parallel programs with high communication overhead.

• Journal of IKEEE
• /
• v.1 no.1 s.1
• /
• pp.31-46
• /
• 1997

In this paper, a parallel Optimal Best-First search Branch-and-Bound(B&B) algorithm(pobs) is designed and evaluated for MIN-based multiprocessor systems. The proposed algorithm decomposes a problem into G subproblems, where each subproblem is processed on a group of P processors. Each processor group uses tile sub-Global Best-First search technique to find a local solution. The local solutions are broadcasted through the network to compute the global solution. This broadcast provides not only the comparison of G local solutions but also the load balancing among the processor groups. A performance analysis is then conducted to estimate the speed-up of the proposed parallel B&B algorithm. The analytical model is developed based on the probabilistic properties of the B&B algorithm. It considers both the computation time and communication overheads to evaluate the realistic performance of the algorithm under the parallel processing environment. In order to validate the proposed evaluation model, the simulation of the parallel B&B algorithm on a MIN-based system is carried out at the same time. The results from both analysis and simulation match closely. It is also shown that the proposed Optimal Best-First search B&B algorithm performs better than other reported schemes with its various advantageous features such as: less subproblem evaluations, prefer load balancing, and limited scope of remote communication.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3583-3597
• /
• 2020

In this paper, a parallel deep learning model using a convolutional neural network and a dilated convolutional neural network is proposed to classify Alzheimer's disease with high accuracy in PET/CT images. The developed model consists of two pipelines, a conventional CNN pipeline, and a dilated convolution pipeline. An input image is sent through both pipelines, and at the end of both pipelines, extracted features are concatenated and used for classifying Alzheimer's disease. Complimentary abilities of both networks provide better overall accuracy than single conventional CNNs in the dataset. Moreover, instead of performing binary classification, the proposed model performs three-class classification being Alzheimer's disease, mild cognitive impairment, and normal control. Using the data received from Dong-a University, the model performs classification detecting Alzheimer's disease with an accuracy of up to 95.51%.