다중 이동 에이전트 제어를 위한 위치 관리 기법

윤준원(JunWeon Yoon),강석준(SeokJun Kang),최성진(SungJin Choi),손진곤(ChongSun Hwang),황종선(JinGon Shon) 한국정보과학회 2003 한국정보과학회 학술발표논문집 Vol.30 No.2Ⅲ

여러 지역으로 구성된 다중 이동 에이전트 컴퓨팅 환경에서 에이전트들을 관리하기 위한 위치 관리 기법은 이동 에이전트 시스템을 개발하는데 있어서 중요한 고려 사항이다. 그러나, 기존의 연구에서는 단지 하나의 이동 에이전트를 통제하기 위한 위치 관리만을 고려할 뿐 같은 작업을 수행하는 다중 이동 에이전트들을 통제하는 위치 관리 기법은 다루지 않고 있다. 따라서, 이전 기법을 다중 이동 에이전트를 관리하는데 적용하면 다중 이동 에이전트들을 관리하는 비용은 증가하게 된다. 본 논문에서는 여러 지역으로 구성된 이동 에이전트 컴퓨팅 환경에서 다중 이동 에이전트 관리를 위한 위치 관리 기법인 WSC(Workname Search and Control)기법을 제안하고자 한다. 제안된 기법은 다중 이동 에이전트 관리를 위한 모델을 제시함으로써 다중 이동 에이전트 관리를 위한 메시지 전달 부하를 감소시킨다.

AI를 위한 파일시스템 병렬 I/O 기술 연구

윤준원 ( Junweon Yoon ),홍태영 ( Taeyeong Hong ) 한국정보처리학회 2022 한국정보처리학회 학술대회논문집 Vol.29 No.2

대규모 데이터를 처리하기 위해 머신러닝, 딥러닝과 같은 AI 활용 연구가 일반화되면서 시스템 환경 또한 병렬처리 연산에 강화된 가속기 기반의 이기종 아키텍처로 확산되고 있다. CPU 기반의 계산 환경과 달리 상대적으로 성능이 낮은 수천 개의 산술연산장치(ALU)를 활용해 쓰레드 방식으로 연산을 수행하며, I/O의 특성 또한 대규모의 데이터들이 수많은 연산장치에 전달되기 위한 Small I/O, High-throughput 처리 성능이 애플리케이션에 큰 영향을 끼친다. 본 논문에서는 병렬 컴퓨팅 환경에 AI 애플리케이션이 접목되면서 요구되는 스토리지, 파일시스템의 환경을 분석하고 나아가 성능 검증을 통해 I/O 특성을 파악하고자 한다.

고성능 I/O 지원을 위한 계층형 스토리지 구현

윤준원 ( Junweon Yoon ),홍태영 ( Taeyeong Hong ) 한국정보처리학회 2023 한국정보처리학회 학술대회논문집 Vol.30 No.2

ML/DL과 같은 AI의 연구가 HPC 환경에서 수행되면서 데이터 병렬화, 분산 학습 및 대규모 데이터 세트를 처리를 위한 요구사항이 급격히 증가하였다. 또한, 병렬처리 연산에 특화된 가속기 기반 이기종 아키텍처 환경 변화로 I/O 처리에 고대역폭, 저지연의 스토리지 기술을 필요로 하고 있다. 본 논문에서는 고집적의 병렬 컴퓨팅 환경에 고성능 HPC, AI 애플리케이션을 처리하기 위한 티어링 스토리지 기술을 논한다. 나아가 실제 고성능 NVMe 기반의 플래시 티어링 계층 구성에서 액세스 패턴에 따른 데이터 처리 환경을 구축하고 성능을 검증한다. 이로써 다양한 사용자 어플리케이션의 I/O 패턴을 특성에 맞게 지원할 수 있다.

성능분석을 통한 안정화된 클라우드 컴퓨팅 기반 교육 실습 시스템 구축

윤준원(JunWeon Yoon),송의성(Ui-Sung Song) 한국디지털콘텐츠학회 2014 한국디지털콘텐츠학회논문지 Vol.15 No.5

Cloud computing is already well known paradigm that a support computing resource flexible and scalable to users as the want in distributed computing environment. Actually, cloud computing can be implemented and provided by virtualization technology. Also, various products are released or under development. In this paper, we built the teaching practice system using cloud computing and evaluated practical environment which constructed over a virtual machine. Virtualization-based cloud computing provides optimized computing resources, as well as easy to manage practical resource and result. Therefore, we can save the time for configuration of practice environment. In the view of faculty, they can easily handle the practice result. Also, those practice condition reuse comfortably and apply to various configuration simply. And then we can increase capabilities and availabilities of limited resources. Additionally, we measure the performance requirements for educational applications through evaluation of virtual-based teaching practical system in advance.

HPC 환경에서 사용자 로그 분석을 통한 작업 성공률 개선

윤준원(JunWeon Yoon),홍태영(TaeYoung Hong),공기식(Ki-Sik Kong),박찬열(ChanYeol Park) 한국디지털콘텐츠학회 2015 한국디지털콘텐츠학회논문지 Vol.16 No.5

Supercomputers are used for many different areas including new product design of industries as well as state-of-the-art science and technology for large amount of computational needs. Tachyon is a 4th supercomputer built at KISTI that is a high-performance parallel computing system with 3,200 computing nodes and infrastructures. This system is currently about 10,000 users and over 170 organizations are used, the number of jobs they are performing work in batch type form through a scheduler. Also, this system logs lots of job scripts, execution environment, library, job status from the job submit to end. In this paper, we analyzed batch jobs information from Sun Grid Engine, that use as a scheduler in Tachyon system, and job executed information in Tachyon System. In particular, we distinguished the fail jobs from the all tasks that users perform and we analyzed the cause of failure. Among them, we can extracted some of jobs that can be regarded as normal jobs through the improvement in those works logged as all of fail jobs.

분산 컴퓨팅 기술을 이용한 고해상도 강수량 예측

윤준원(JunWeon Yoon),송의성(Ui-Sung Song) 한국디지털콘텐츠학회 2016 한국디지털콘텐츠학회논문지 Vol.17 No.1

Distributed Computing attempts to harness a massive computing power using a great numbers of idle PCs resource distributed linked to the internet and processes a variety of applications parallel way such as bio, climate, cryptology, and astronomy. In this paper, we develop internet-distributed computing environment, so that we can analyze High Resolution Rainfall Prediction application in meteorological field. For analyze the rainfall forecast in Korea peninsula, we used QPM(Quantitative Precipitation Model) that is a mesoscale forecasting model. It needs to a lot of time to construct model which consisted of 27KM grid spacing, also the efficiency is degraded. On the other hand, based on this model it is easy to understand the distribution of rainfall calculated in accordance with the detailed topography of the area represented by a small terrain model reflecting the effects 3km radius of detail and terrain can improve the computational efficiency. The model is broken down into detailed area greater the required parallelism and increases the number of compute nodes that efficiency is increased linearly. This model is distributed divided in two sub-grid distributed units of work to be done in the domain of 20X20 is networked computing resources.

병렬 분산파일시스템의 성능 분석을 통한 최적화 연구

윤준원(JunWeon Yoon),송의성(Ui-Sung Song) 한국디지털콘텐츠학회 2016 한국디지털콘텐츠학회논문지 Vol.17 No.5

Recently, Big Data issue has become a buzzword and universities, industries and research institutes have been efforts to collect, analyze various data enabled. These things includes accumulated data from the past, even if it is not possible to analysis at this present immediately a which has the potential means. And we are obtained a valuable result from the collected a large amount of data via the semantic analysis. The demand for high-performance storage system that can handle large amounts of data required is increasing around the world. In addition, it must provide a distributed parallel file system that stability to multiple users too perform a variety of analyzes at the same time by connecting a large amount of the accumulated data In this study, we identify the I/O bandwidth of the storage system to be considered, and performance of the metadata in order to provide a file system in stability and propose a method for configuring the optimal environment.

클라우드 교육 시스템의 SLA 보장을 위한 오픈소스기반 요소 성능 분석

윤준원(JunWeon Yoon),송의성(Ui-Sung Song) 한국디지털콘텐츠학회 2017 한국디지털콘텐츠학회논문지 Vol.18 No.1

As the increasing use of the cloud computing, virtualization technology have been combined and applied a variety of requirements. Cloud computing has the advantage that the support computing resource by a flexible and scalable to users as they want and it utilized in a variety of distributed computing. To do this, it is especially important to ensure the stability of the cloud computing. In this paper, we analyzed a variety of component measurement using open-source tools for ensuring the performance of the system on the education system to build cloud testbed environment. And we extract the performance that may affect the virtualization environment from processor, memory, cache, network, etc on each of the host machine(Host Machine) and a virtual machine (Virtual Machine). Using this result, we can clearly grasp the state of the system and also it is possible to quickly diagnose the problem. Furthermore, the cloud computing can be guaranteed the SLA(Service Level Agreement).

암호학 응용 해결을 위한 데스크톱 그리드 컴퓨팅 기술

윤준원(JunWeon Yoon),최장원(JangWon Choi),이필우(PillWoo Lee),길민준(JoonMin Gil),홍석희(SeokHee Hong) 한국정보기술학회 2009 한국정보기술학회논문지 Vol.7 No.5

Desktop grid attempts to harness a massive computing power using a great numbers of PCs distributedly linked to the Internet. Also, those PCs join and donate their PC resources volunteerly. The computing power is used to process the massive information which is difficulty of working in a single process. Korea@Home project is running and solving large-scale distributed/parallel application problems such as bio, climate, cryptology, and astronomy. Volunteers can participate in Korea@Home project from anywhere on Internet to contribute their own PC's idle time. In this paper we develop and apply to a cryptology application that can execute Korea@Home which is Desktop Grid platform. In cryptography analysis, It is important to identify the correct key is in quick time. Especially, in this paper implemented TMTO(Time-Memory Trade-Off) method through software and applies to Korea@Home. And then we can get a cryptanalysis technology and stability evaluation. Now, the stability of the cryptanalysis algorithm since the 56-bit key length is increased and then more calculations are required. Future, if the desktop grid infrastructure is expanded and we get an appropriate TMO attack, we can secure more stable cryptography.

데스크톱 그리드 기반 한국형 외계지적생명체 탐색

윤준원(JunWeon Yoon),최장원(JangWon Choi),변용익(YongIk Byun),이명현(MyungHyun Rhee),유헌창(HeonChang Yu) 한국정보기술학회 2010 한국정보기술학회논문지 Vol.8 No.12

Desktop grid attempts to harness a massive computing power using a great numbers of idle PCs resource distributed linked to the Internet and processes a variety of applications parallel way. Korea@Home project is the nation's first desktop grid platform that executes diverse applications of science and technology area. In this paper, we develop algorithms and computing environment, so that we can utilize Korea@Home platform and the incoming data from KVN facilities for a large scale desktop grid computing for SETI-VLBI. In the future, SETI application execution in astronomy using Korea@Home become more important issues if the KJJVC(Korea-Japan Joint VLBI Correlator : KJJVC) East Asian Network, combined VLBI network consisting of KVN and VERA including several other telescope, is constructed.