• 정보처리학회논문지A
• /
• 제10A권1호
• /
• pp.25-34
• /
• 2003

병렬 파일 시스템은 고속의 네트웍으로 여러 대의 컴퓨터들을 서로 연결하여 컴퓨터들 간에 메시지를 주고받으면서 파일을 분산 저장하고 병렬로 읽어오는 방식으로 파일 입출력 장치의 병목현상을 해결한다. 그러나 대부분의 병렬 파일 시스템은 전달하려는 메시지의 특성을 고려하지 않은 프로토콜의 사용으로 성능저하의 문제를 가지고 있다. 이에 따라 본 논문에서 메시지 처리 방법으로 HCM(Hybrid Channel Model)을 제안한다. 본 논문에서 제안하는 HCM은 병렬 파일 시스템에서 전달되는 메시지를 그 특성에 따라 분리해서 별개의 프로토콜을 이용하여 제어 메시지와 파일 데이터 블록을 전송한다. 안정성이 검증된 TCP/IP를 이용하여 구현한 메시지 채널을 통해 제어 메시지를 고속의 데이터 전송이 가능한 VIA를 이용하여 구현한 데이터 채널을 통해 파일 데이터 블록을 각각 분리하여 처리하도록 하고 있다 HCM을 병렬 파일 시스템에 구현하고 실험해본 결과 본 논문에서 제안한 채널 모델이 상당한 성능향상을 보였다.

• Nuclear Engineering and Technology
• /
• 제41권6호
• /
• pp.807-812
• /
• 2009

An ICRF discharge cleaning and a fast wave electron heating experiment were performed. For automated operation and providing the diagnostics of the ICRF system, the ICRF local network was designed and implemented. This internal network provides monitoring, RF protection, remote control, and RF diagnostics. All the functions of the control system were realized by customized DSP units. The DSP units were tied by a local network in parallel. Owing to the distributed feature of the control system, the ICRF local control system is quite flexible to maintain. Developing the subsystem is a more effective approach compared to developing a large controller that governs the entire system. During the first experimental campaign of the KSTAR tokamak, the control system operated as expected without any major problems that would affect the tokamak operation. The transmitter was protected from harmful over-voltage events through reliable operation of the system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3182-3202
• /
• 2015

Flexibly expanding the storage capacity required to process a large amount of rapidly increasing unstructured log data is difficult in a conventional computing environment. In addition, implementing a log processing system providing features that categorize and analyze unstructured log data is extremely difficult. To overcome such limitations, we propose and design a MongoDB-based unstructured log processing system (MdbULPS) for collecting, categorizing, and analyzing log data generated from banks. The proposed system includes a Hadoop-based analysis module for reliable parallel-distributed processing of massive log data. Furthermore, because the Hadoop distributed file system (HDFS) stores data by generating replicas of collected log data in block units, the proposed system offers automatic system recovery against system failures and data loss. Finally, by establishing a distributed database using the NoSQL-based MongoDB, the proposed system provides methods of effectively processing unstructured log data. To evaluate the proposed system, we conducted three different performance tests on a local test bed including twelve nodes: comparing our system with a MySQL-based approach, comparing it with an Hbase-based approach, and changing the chunk size option. From the experiments, we found that our system showed better performance in processing unstructured log data.

• Journal of the Korean Data and Information Science Society
• /
• 제26권5호
• /
• pp.1129-1139
• /
• 2015

시멘틱 웹 기술인 RDF 트리플로 표현된 지식을 추론 과정을 거치면 새로운 트리플들이 생성되어 나온다. 초기 입력된 수억개의 트리플로 구성된 빅데이터와 추가로 생성된 트리플 데이터를 바탕으로 질의응답과 같은 다양한 응용시스템이 만들어 진다. 이 추론기가 수행되는 과정에서 더 많은 컴퓨팅 리소스가 필요해 진다. 이 추가 컴퓨팅 리소스는 하부 클라우드 컴퓨팅의 리소스 풀로부터 공급받아 수행시간을 줄일 수 있다. 본 연구에서는 하둡을 이용하는 환경에서 지식의 크기에 따라 런타임에 동적으로 서버 컴퓨팅 노드를 증감 시키는 방법을 연구하였다. 상부는 응용계층이며, 중간부는 트리플들에 대한 분산병렬추론과 하부는 탄력적 하둡시스템 및 가상화 서버로 구성되는 계층적 모델을 제시한다. 이 시스템의 알고리즘과 시험성능의 결과를 분석한다. 하둡 상에 기 개발된 풍부한 응용소프트웨어들은 이 탄력적 하둡 시스템 상에서 수정 없이 보다 빨리 수행될 수 있는 장점이 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.974-979
• /
• 1990

The system discussed in this paper is an integrated stand-alone system with the full functional capabilities required of a telerobot system. It is complete with a force-reflecting 6-DOF hand controller, driving a PUMA 560 or 762 robot, with an integrated force-torque sensing wrist sensor and servo-driven parallel jaw gripper. A mix of custom and standard electronics, distributed computers and microprocessors, with embedded and downloadable software, have been integrated into the system, giving rise to a powerful and flexible teleautonomous control system.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 춘계학술대회 논문집
• /
• pp.619-620
• /
• 2006

In this paper, the CAE Service System for Collaborative Engineering Environment with web services and Multi-frontal Method has been investigated and developed. The enabling technologies such as SOAP and .NET Framework play great roles in the development of integrated distributed application software. In addition to the distribution of analysis modules, numerical solution process itself is again divided into parallel processes using Multi-frontal Method for computational efficiency. We believe that the proposed approach for the analysis can be extended to the entire product development process for sharing and utilizing common product data in the distributed engineering environment.

• 한국군사과학기술학회지
• /
• 제13권1호
• /
• pp.9-21
• /
• 2010

In this paper, optimum design of distributed detection is considered for a parallel sensor network system consisting of a fusion center and multiple passive sonar nodes. Nonrandom fusion rules are employed as the fusion rules of the sensor network. For the nonrandom fusion rules, it is shown that a threshold rule of each sensor node has uniformly most powerful properties. Optimum threshold for each sensor is investigated that maximizes the probability of detection under a constraint on energy consumption due to false alarms. It is also investigated through numerical experiments how signal strength, false alarm probability, and the distance between three sensor nodes affect the system detection performances.

• 정보화연구
• /
• 제10권3호
• /
• pp.387-397
• /
• 2013

본 연구는 전화통화에 의해 생성된 데이터에 대한 빅데이터 분석 접근을 제안한다. 전화통화 데이터의 분석모형은 자연어의 어휘식별을 위한 PVPF(Parallel Variable-length Phrase Finding) 알고리즘과 키워드의 사용빈도 측정을 위한 워드 카운트 알고리즘으로 구성된다. 제안한 분석모형에서는 먼저 PVPF 알고리즘에 의해 연계 단어 추출을 통해 어휘를 식별하며, MapReduce의 워드 카운트 알고리즘을 사용하여 식별된 어휘 및 단어의 사용빈도를 측정한다. 그 결과는 다양한 관점에서 해석될 수 있다. 제안 분석모형의 효과성을 보이기 위해 HDFS(Hadoop Distributed File System)를 기반으로 분석모형을 설계 구현하였으며, 전화통화 데이터를 실험 적용한다. 실험결과, 키워드 상관관계 분석 및 사용빈도 변화 분석을 통해 유의미한 결과를 도출한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 춘계학술발표대회
• /
• pp.476-477
• /
• 2013

Gadget-2 is a scientific simulation code has been used for many different types of simulations like, Colliding Galaxies, Cluster Formation and the popular Millennium Simulation. The code is parallelized with Message Passing Interface (MPI) and is written in C language. There is also a Java adaptation of the original code written using MPJ Express called Java Gadget. Java Gadget writes a lot of checkpoint data which may or may not use the HDF-5 file format. Since, HDF-5 is MPI-IO compliant, we can use our MPJ-IO library to perform parallel reading and writing of the checkpoint files and improve I/O performance. Additionally, to add reliability to the code execution, we propose the usage of Hadoop Distributed File System (HDFS) for writing the intermediate (checkpoint files) and final data (output files). The current code writes and reads the input, output and checkpoint files sequentially which can easily become bottleneck for large scale simulations. In this paper, we propose Sim-Hadoop, a framework to leverage HDFS and MPJ-IO for improving the I/O performance of Java Gadget code.

• 한국태양에너지학회 논문집
• /
• 제33권5호
• /
• pp.105-112
• /
• 2013

The new renewable energy became popular as a clean and sustainable alternative energy under the circumstances that the entire world is facing severe abnormal climate due to the use of fossil fuel, and among which, solar energy can be obtained anywhere and is not difficult to apply it into the existing buildings, which makes it possible to be widely distributed. However, as PV module is installed into a single plate system, it shows structural weaknesses which are vulnerable to wind load and give loss to design elements in external appearance. Accordingly, this study planned one-step parallel system to complement the problems occurring from a single plate system and used STAR-CCM+ V.8 made by CD-Adapco, a computational fluid dynamics(CFD) simulation tool to measure wind load stability and support based on the design standards for a single plate system and one-step parallel system. Building height was limited to less than 10m and wind speed was given when increasing from 35m/s to 50m/s by 5m/s on PV system installed into the flat roof. In this case, our analysis suggested that step-one parallel system was in class 7-9 according to Beaufort's wind power classification, which did not have an impact on the fixed PV system, and the single plate system is considered to cause risks in designing wind speed in central districts because it is more than wind power class 12.