• 한국컴퓨터정보학회논문지
• /
• 제22권4호
• /
• pp.17-24
• /
• 2017

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.147-153
• /
• 2016

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.125-129
• /
• 2016

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• 정보학연구
• /
• 제5권4호
• /
• pp.35-44
• /
• 2002

자바의 이전성은 해석 방식에 따른 비효율성을 낳는다. 또한 일반 응용 프로그램에서 자바의 표준 클래스 라이브러리는 플랫폼 의존적인 기능을 제공하지 못한다. 이러한 여러 가지 문제를 해결하기 위해 JNI, JIT, 오프라인 바이트코드 컴파일러가 제안되어왔다. 본 논문에서는 자바 가상기계가 네이티브 코드와 함께 실행되는 혼합형 실행 모델을 제시한다. 현 실행 모델과 번역기는 동적으로 바이트코드를 적재할 수 있는 능력이 주어지며 JNI의 수월한 사용을 제공한다. 본 시스템은 JIT 보다 효율적이며, JNI의 개념이 부족한 프로그래머가 쉽게 네이티브코드 작성할 수 있도록 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권6호
• /
• pp.1237-1252
• /
• 2010

This paper proposes an intelligent technique for data sharing and event transition among personal devices including smart phones, laptops, and desktops. We implemented the PES (Personal Event Service) system that proactively executes appropriate tasks across multiple devices without explicit user requests by sharing the data used by the user and recognizing user intention based on the observed actions of the user for specific devices. The client module of PES installed on each device monitors the user actions and recognizes the intention of the user. The server provides data sharing and maintenance for clients. The connection between client and server is established by Java RMI (Remote Method Invocation). A series of experiments were performed to evaluate user satisfaction and system accuracy, and the results showed that the PES system can proactively provide appropriate, personalized services with a high degree of satisfaction to the user in an effective and efficient manner.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 춘계학술대회 논문집
• /
• pp.199-205
• /
• 2008

The monorail system as new transportation system mostly has being constructed as an elevated construction and the track beam as mostly main work type occupy the important parts. The structure of monorail system, the track beam support directly vehicle's load and comprised of the track beam structure to be traveling side and understructure to be transmitted from their load to the ground. In particular, in case of construction to elevated structure in the center of a city, it is important to decision plan for span to be considered the economic, execution and maintenance according to transport, installation, and the structure problem, scene and civil appeals to be decided the beam elevation and span. Therefore the standard span of monorail track beam shall be considered the efficient execution, economic and transportation. And propose to reasonable decision plan incorporated the minimizing the road occupied width due to openness to center of a city and bridge pole, minimize to basis size.

• 한국전자거래학회지
• /
• 제9권4호
• /
• pp.65-83
• /
• 2004

기업간 경쟁의 격화와 정보기술의 발달로 인하여 많은 기업들이 공급사슬관리(SCM)를 도입하고 있다. 이에 따라, 공급사슬상의 관련 기업간의 상호작용과 정보공유에 기반한 공급사슬 통합이 추진되고 있으며, 웹서비스 와 같은 시스템에 독립적인 기술 적용의 필요성이 제기되고 있다. 웹서비스를 이용하면서도 높은 수준의 공급사슬 통합이 이루어지기 위해서는, 여러 상호작용주체가 참여하는 글로벌 프로세스 수준에서 SCM 프로세스를 관리하고 제어할 필요가 있으며, 본 논문에서는 비즈니스 프로세스 자동화 및 관리도구로 최근 각광을 받고 있는 BPM을 도입하여 각 업무단위가 웹서비스로 구성된 환경에서 SCM을 구성하는 프로세스를 효과적으로 통합하여 실행하는 방안을 제시한다. 이러한 접근법은 SCM 프로세스의 진행과정을 보다 효율적으로 관리, 모니터링하는 것이 가능하며, SCM 프로세스의 수행결과를 토대로 프로세스의 개선에 대한 방안을 모색할 수 있다. 또한, SCM 프로세스의 진행과정에서 의사결정이 필요한 경우 이에 대한 지원 에이전트를 웹서비스로 구성하여 보다 신속한 프로세스 수행을 가능하게 한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 추계종합학술대회
• /
• pp.131-134
• /
• 2005

본 논문에서는 이동에이전트 기반으로 구축된 P-그리드 환경에서, 그리드 서비스 에이전트가 각 피어에게 효율적으로 이주할 수 있는 방법에 대하여 연구한다. 서비스 요청에 따른, 서비스 에이전트를 전달하기 위한 이주방법은 피어의 논리적인 네트워크 위상에 기반한다. 본 시스템에서 사용되는 네트워크 위상은 스타형 위상, 링형 위상, 트리형 위상으로 구성되어, 마스터/슬레이브 방식과 직렬 및 병렬 전송방식으로 에이전트를 이주시킨다. 요청된 서비스의 수행범위 및 특성에 따라 서비스 에이전트의 이주방식을 선택한다. 또한 네트워크 위상을 구성하는 피어의 성능과 에이전트 이주 순서에 의해 서비스 전체 수행시간이 영향을 받는다. 따라서 피어의 성능을 모니터링하고, 히스토리를 분석 및 학습하여 에이전트의 이주 우선순위를 결정한다. 서비스 에이전트의 이주방식의 결정과 이주하려는 피어의 우선순위 결정을 통하여 효율적으로 서비스 수행시간을 절감할 수 있다.

• 대한임베디드공학회논문지
• /
• 제7권5호
• /
• pp.241-246
• /
• 2012

As the convergence between the conventional physical systems and IT computing resource is increased, the new paradigm of embedded system called Cyber Physical System (CPS) emerged. CPSs have many sensors, actuators and computing devices to understand and to control the physical system. As these all components are tightly coupled each other, standardized middleware such as Data Distribution Service (DDS) is considered to be deployed. But DDS takes too long time to discover each other in the large-scal CPS environment and has not precise specification of its execution architecture to provide efficient data exchange. In this paper, we design the efficient DDS architecture for development with interoperability to provide the high reliable data distribution. in real-time and propose the communication entity discovery procedure.

• 대한전자공학회논문지
• /
• 제24권2호
• /
• pp.315-323
• /
• 1987

Generally, general-purpose image processing system is so expensive that not so many users easily can access the system. In this paper attemps have been made to design and describe a general and economical image processing system for real-time aplications such as image data compression, pattern recognition and target tracking. The system comprises an operator console, image data acquisition/display sistem and IBM PC/XT. The system also utilizes a high speed Fairchild 16-bit microprocessor with ALU speed of 375 nsec for system control, algrithm execution and user computation. The system also can digitize /display a 256x 256x 8 bit image in real time and store two frames of images. All image pixels are directly accessible by the microprocessor for fast and efficient computation. Some experimental and illustrative results such as target tracking are presented to show the efficient performance of the system.