• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.333-336
• /
• 2000

We discuss the direct methods (Gauss-Jordan and Gaussian eliminations) to solve linear systems on distributed memory parallel computers. It will be shown that the so-called row-cyclic storage gives rise to the best performance among the standard three (row-cyclic, column-cyclic and cyclic-cyclic) data storages. We also show that Gauss-Jordan elimination, rather than Gaussian elimination, is highly efficient for the direct solution of linear systems in parallel processing, though Gauss-Jordan elimination requires a larger number of arithmetic operations than Gaussian elimination. Numerical experiment is performed on HITACHI SR12201 with the standard libraries MPI and BLAS.

• 한국컴퓨터정보학회논문지
• /
• 제22권11호
• /
• pp.57-63
• /
• 2017

The recent sudden increase of big data has characteristics such as continuous generation of data, large amount, and unstructured format. The existing relational database technologies are inadequate to handle such big data due to the limited processing speed and the significant storage expansion cost. Thus, big data processing technologies, which are normally based on distributed file systems, distributed database management, and parallel processing technologies, have arisen as a core technology to implement big data repositories. In this paper, we propose a design methodology for large-scale database based on MongoDB by extending the information engineering methodology based on E-R data model.

• 전기학회논문지
• /
• 제61권9호
• /
• pp.1289-1295
• /
• 2012

An active resonance damper for a DC Distributed Power System(DPS) with parallel loads is presented. Each pulse power load in a DC DPS comprises both a resistive power load and a step-up converter. The step-up converter behave as constant power load(CPL) when tightly regulated and usually cause a negative impedance instability problem. Furthermore, when an input filter is connected to a large constant power load, the instability of DC bus voltage. In this paper, a bidirectional DC/DC converter with a reduced storage capacitor quantitatively are proposed as a active resonance damper, to mitigate the voltage instability on the bus. The validity of the proposed method was confirmed by simulation and experimental works.

• Asia pacific journal of information systems
• /
• 제1권1호
• /
• pp.49-62
• /
• 1991

This paper examines the problems of database partitioning and file allocation in a fixed topology distributed computer network. The design objective is to make files as collections of attributes and to allocate these files to network nodes so that a minimum total transmission cost is achieved subject to storage capacity constraints. A mathematical model for solving the problem is formulated and, the resulting optimization problem is shown to fall in a class of NP-complete problems. A new heuristic algorithm is developed which uses the idea of allocating attributes according to the transaction requirements at each computer node and then making files using the allocated attributes. Numerical results indicate that the heuristic algorithm yields practicable low cost solutions in comparison with the existing methods which deal with the file allocation problems and database partitioning problems independently.

• International Journal of Contents
• /
• 제17권3호
• /
• pp.74-83
• /
• 2021

A location-aware algorithm is proposed in this study to optimize the system performance of distributed systems for processing big data with low data reliability and application performance. Compared with previous algorithms, the location-aware data block placement algorithm uses data block placement and node data recovery strategies to improve data application performance and reliability. Simulation and actual cluster tests showed that the location-aware placement algorithm proposed in this study could greatly improve data reliability and shorten the application processing time of I/O interfaces in real-time.

• 전자통신동향분석
• /
• 제34권1호
• /
• pp.13-22
• /
• 2019

Various hyper-intelligent and ultra-realistic data-driven services are being increasingly developed with the goal of achieving a hyper-connected intelligent society. To sustain this trend, our research focuses on the integration and optimization of data-driven applications from several aspects such as delivery, storage, execution, and sharing of data and software, beyond the limitations of the existing network infrastructure. In this paper, we present important research issues of data-centric hyper-distributed autonomous infrastructure technologies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2429-2449
• /
• 2018

Dynamic data possession verification is a common requirement in cloud storage systems. After the client outsources its data to the cloud, it needs to not only check the integrity of its data but also verify whether the update is executed correctly. Previous researches have proposed various schemes based on Merkle Hash Tree (MHT) and implemented some initial improvements to prevent the tree imbalance. This paper tries to take one step further: Is there still any problems remained for optimization? In this paper, we study how to raise the efficiency of data dynamics by improving the parts of query and rebalancing, using a new data structure called Rank-Based Merkle AVL Tree (RB-MAT). Furthermore, we fill the gap of verifying multiple update operations at the same time, which is the novel batch updating scheme. The experimental results show that our efficient scheme has better efficiency than those of existing methods.

• Journal of Electrical Engineering and Technology
• /
• 제10권5호
• /
• pp.1983-1988
• /
• 2015

This paper proposes the enhanced application of superconducting magnetic energy storage (SMES) for the effective compensation of power fluctuations based on the interleaving technique. With increases in demand for renewable energy based photovoltaic (PV) generation system, the output power fluctuations from PV generation system due to sudden changes in environmental conditions can cause serious problems such as grid voltage and frequency variations. To solve this problem, the SMES system is applied with its superior characteristics with respect to high power density, fast response for charge and discharge operations, system efficiency, etc. In particular, the compensation capability is effectively improved by the proposed interleaving technique based on its parallel structure. The dynamic performance of the system designed using the proposed method is evaluated with several case studies through time-domain simulations.

• 산업경영시스템학회지
• /
• 제27권3호
• /
• pp.26-30
• /
• 2004

We consider an AS/RS(Automated Storage/ Retrieval System) which performs both of single and dual commands. The service times of single and dual commands are assumed to be differently distributed. Steady-state probabilities at the service completion epochs are calculated. Then, we transform the arrival rates of storage and retrieval commands into those of single and dual commands. Using this, we propose a non-preemptive queueing model with priority for the performance analysis of an AS/RS, and obtain approximated means of queue lengths and waiting times.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2015년도 제46회 하계학술대회
• /
• pp.521-522
• /
• 2015

Many countries concern about environmental problems. Therefore, they have made regulation for mandatory reduction of greenhouse gases. Electric Vehicles(EVs) are one of the most effective counterproposals for it. EVs are usually charging for it by using actual distribution system of the Korea Electric Power Corporation(KEPCO). However, it could cause adverse effects such as increase of the power demand and voltage variation on the distribution system. To reduce adverse effects for demand power side, in this paper, charging for EVs by using PV(Photovolatic Power Generation) connected with ESS(Energy Storage System) are modeled by using Electro Magnetic Transient Program(EMTP). And then, the simulation results are compared with EVs that are connected to the distribution system of KEPCO for using charge.