• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.7
• /
• pp.304-318
• /
• 2007

Grid computing is a service that share geographically distributed computing resources through high speed network. In this paper, we propose hybrid scheduling scheme which considers not only meta-scheduling scheme to distribute the job between the nodes of grid computing system but also the job scheduling to distribute the job within the local nodes. According to the number of processors needed and expected execution time, the job with high priority is allocated to job queue while the one with low priority and remote job are allocated to backfill queue. We evaluate the proposing scheme through the various experiments and the results show that the utilization of grid computing system increases and the job slowdown decreases.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.7
• /
• pp.13-23
• /
• 2011

Grid computing is a new generation computing technology which organizes virtual high-performance computing system by connecting and sharing geographically distributed heterogeneous resources, and performing large-scaled computing operations. In order to maximize the performance of grid computing, job scheduling is essential which allocates jobs to resources effectively. Many studies have been performed which minimize total completion times, etc. However, resource costs are also important, and through the minimization of resource costs, the overall performance of grid computing and economic efficiency will be improved. So in this paper, we propose a multi-objective job scheduling model considering both time and cost. This model derives from the optimal scheduling solution using NSGA-II, which is a multi objective genetic algorithm, and guarantees the effectiveness of the proposed model by executing experiments with those of existing scheduling models such as Min-Min and Max-Min models. Through experiments, we prove that the proposed scheduling model minimizes time and cost more efficiently than existing scheduling models.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.7-9
• /
• 2003

여러 지역에 산재되어 있는 고성능의 컴퓨팅 자원들을 이용하는 그리드에서는 어떠한 자원을 선택하느냐에 따라 응용 프로그램의 성능이 좌우된다. 본 논문에서는 단일 클러스터의 노드 개수에 우선한 스케줄링 방법과 노드의 속도를 우선으로 한 스케줄링 방법을 고려하였다. 이러한 실험을 위하여 스케줄링 구조를 설계하고 그리드 자원에서 실제 실험하여 결과를 비교하였다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.429-439
• /
• 2006

A desktop grid, which is a computing grid composed of idle computing resources in a large network of desktop computers, is a promising platform for compute-intensive distributed computing applications. However, due to reliability and unpredictability of computing resources, effective scheduling of parallel computing applications on such a platform is a difficult problem. This paper proposes a new scheduling method aimed at reducing the total execution time of a parallel application on a desktop grid. The proposed method is based on utilizing the histories of execution behavior of individual computing nodes in the scheduling algorithm. In order to test out the feasibility of this idea, execution trace data were collected from a set of 40 desktop workstations over a period of seven weeks. Then, based on this data, the execution of several representative parallel applications were simulated using trace-driven simulation. The simulation results showed that the proposed method improves the execution time of the target applications significantly when compared to previous desktop grid scheduling methods. In addition, there were fewer instances of application suspension and failure.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.8
• /
• pp.753-757
• /
• 2008

In this paper, we propose a new scheduling strategy for dynamic programming in Grid environment. The key idea of this scheme is to reduce the execution time of a job by dividing the dynamic table based on the locality of table and allocating jobs to nodes which minimize network latency. This scheme obtains optimal concurrency by constructing the dynamic table using a distributed top down method. Through simulation, we show that the proposed Grid strategy improves the performance of Grid environment compared to previous branch-bound strategies.

• Journal of the Korea Society for Simulation
• /
• v.15 no.3
• /
• pp.31-37
• /
• 2006

To achieve the efficient performance within a mobile grid considering the intermittent network connectivity and non-dedicated heterogeneous mobile devices, this paper suggests the scheduling algorithm of job allocation as a viable solution. The suggested scheduling algorithm has two core functions, the prediction of response time for task processing and the identification of the optimal number of mobile devices to process the mobile grid applications. This scheduling algorithm suggests the numerical formulas to calculate the network latency considering the effects of heterogeneous non-dedicated mobile system in wireless network environments. Also we evaluate the performance of mobile grid system using the processing the distributed applications in implemented mobile grid environments.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.424-426
• /
• 2003

웹 서비스의 사용이 급격히 증가함에 따라 사용자의 웹 서비스 005(Quality of Services)에 대란 관심도 높아지고 있다. 본 논문에서는 QoS 요소들 중 응답 시간(Response time) 향상에 대한 스케줄링 기법을 제안하여, 서비스의 질을 향상시키고자 한다. 구체적으로는 기존의 그리드 시스템에 사용되고 있는 단일 배치 스케줄링 기법을 기본으로 한 다중 배치 스케줄링을 연구하였으며, 이를 통해 그리드 기반 웹 서비스의 응답 시간 성능이 개선됨을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.742-744
• /
• 2004

본 논문은 웹 서비스 프로토콜인 SOAP기반의 병렬처리 프레임웍인 pyBubble의 설계와 구현에 관한 것이다. 그리드 어플리케이션 프로그래밍의 어려움을 덜기 위해 그리드 미들웨어들로부터의 복잡성에 투명성을 제공하는 것을 본 논문의 목표로 한다. 이는 RPC스타일의 프로그래밍 인터페이스를 지원하면서 파이썬 스크립트 언어의 이식성과 확장성을 통해 기존 병렬처리 어플리케이션의 그리드화와 다양한 자원 스케줄링을 연구 할 수 있도록 하는 스케줄링 프레임웍이 주요 기능적 요소이다. 병렬처리를 위해 비동기 SOAP과 이를 이용한 Task-Farming과 DAG기반의 스케줄링의 지원함으로써 고성능의 그리드 계산환경을 제공하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.49-51
• /
• 2004

그리드와 웹 서비스가 서로 밀접한 연관성을 가지고 있는 분야로 인식되고 있으면서 그리드 기반 웹 서비스의 QoS(Quality of Services)에 대한 관심이 높아짐과 동시에 중요한 부분으로 여겨지고 있다. 본 논문에서는 QoS 요소들 중 응답 시간(Response time) 향상을 위해서 기존의 그리드 시스템에 사용되고 있는 Easy Backfill 스케줄링 기법을 기본으로 한 다중 큐 스케줄링을 연구하였으며, 또한 기존 Backfill 기법의 큰 작업에 대한 응답 시간이 느려진다는 단점을 보완하기 위해, 각 작업들에 대해서 예약 정책 연구하였다. 이를 통해 그리드 기반 웹 서비스의 응답 시간 성능이 개선됨을 확인하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.5
• /
• pp.375-384
• /
• 2004

The Grid is new infrastructure to provide computing environment for grand challenge research by sharing large-scale resources. Currently the Globus becomes a de facto standard middleware to construct Grid and supports core services such as resource management, security, data transfer, information services, and so on. However, it still needs more works and researches to satisfy requirements from various grid applications. A workflow management is becoming a main service as one of the important grid services for complex grid applications. We propose a Meta Scheduling Framework (MSF) in this paper. The MSF provides a XML-based Job Control Markup Language (JCML) for describing information and procedures of grid applications, and a workflow management service for scheduling the job using the JCML and for processing the job effectively.