• 한국시뮬레이션학회논문지
• /
• 제14권3호
• /
• pp.91-100
• /
• 2005

Grid computing is widely applicable to various fields of industry including process control and manufacturing, military command and control, transportation management, and so on. In a viewpoint of application area, grid computing can be classified to three aspects that are computational grid, data grid and access grid. This paper focuses on computational grid which handles complex and large-scale computing problems. Computational grid is characterized by system dynamics which handles a variety of processors and jobs on continuous time. To solve problems of system complexity and reliability due to complex system dynamics, computational grid needs scheduling policies that allocate various jobs to proper processors and decide processing orders of allocated jobs. This paper proposes a service prediction-based job scheduling model and present its scheduling algorithm that is applicable for computational grid. The service prediction-based job scheduling model can minimize overall system execution time since the model predicts the next processing time of each processing component and distributes a job to a processing component with minimum processing time. This paper implements the job scheduling model on the DEVS modeling and simulation environment and evaluates its efficiency and reliability. Empirical results, which are compared to conventional scheduling policies, show the usefulness of service prediction-based job scheduling.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권1호
• /
• pp.83-104
• /
• 2011

Mobile grid is a combination of grid computing and mobile computing to build grid systems in a wireless mobile environment. The development of network technology is assisting in realizing mobile grid. Mobile grid based on established grid infrastructures needs effective resource management and reliable job scheduling because mobile grid utilizes not only static grid resources but also dynamic grid resources with mobility. However, mobile devices are considered as unavailable resources in traditional grids. Mobile resources should be integrated into existing grid sites. Therefore, this paper presents a mobile grid middleware interconnecting existing grid infrastructures with mobile resources and a mobile service agent installed on the mobile resources. This paper also proposes a mobile resource reliability-based job scheduling model in order to overcome the unreliability of wireless mobile devices and guarantee stable and reliable job processing. In the proposed job scheduling model, the mobile service agent calculates the mobile resource reliability of each resource by using diverse reliability metrics and predicts it. The mobile grid middleware allocated jobs to mobile resources by predicted mobile resource reliability. We implemented a simulation model that simplifies various functions of the proposed job scheduling model by using the DEVS (Discrete Event System Specification) which is the formalism for modeling and analyzing a general system. We also conducted diverse experiments for performance evaluation. Experimental results demonstrate that the proposed model can assist in improving the performance of mobile grid in comparison with existing job scheduling models.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2005년도 춘계학술대회 논문집
• /
• pp.29-33
• /
• 2005

Grid computing is widely applicable to various fields of industry including process control and manufacturing, military command and control, transportation management, and so on. In a viewpoint of application area, grid computing can be classified to three aspects that are computational grid, data grid and access grid. This paper focuses on computational grid which handles complex and large-scale computing problems. Computational grid is characterized by system dynamics which handles a variety of processors and jobs on continuous time. To solve problems of system complexity and reliability due to complex system dynamics, computational grid needs scheduling policies that allocate various jobs to proper processors and decide processing orders of allocated jobs. This paper proposes the service prediction-based job scheduling model and present its algorithm that is applicable for computational grid. The service prediction-based job scheduling model can minimize overall system execution time since the model predicts a processing time of each processing component and distributes a job to processing component with minimum processing time. This paper implements the job scheduling model on the DEVSJAVA modeling and simulation environment and simulates with a case study to evaluate its efficiency and reliability Empirical results, which are compared to the conventional scheduling policies such as the random scheduling and the round-robin scheduling, show the usefulness of service prediction-based job scheduling.

• 한국컴퓨터정보학회논문지
• /
• 제12권5호
• /
• pp.49-56
• /
• 2007

계산 그리드 컴퓨팅은 수많은 컴퓨팅 자원들을 이용하여, 슈퍼 컴퓨팅이나 이전의 분산 컴퓨팅으로 해결 할 수 없는 대용량의 연산 문제를 해결한다. 계산 그리드 컴퓨팅 환경에서의 자원은 이 기종으로 구성되어, 효율적인 작업 처리를 위해서는 스케줄링 기법이 필요하다. 본 논문에서는 계산 그리드에서 효율적인 작업 스케줄링을 위하여 퍼지로직 기반의 그리드 작업 스케줄링 모델을 제안한다. 퍼지로직 기반의 그리드 작업 스케줄링 모델은 퍼지로직을 이용하여 자원의 효율성을 평가하며, 평가된 기반으로 그룹을 구성하여 작업을 할당하는 모델이다. 우리는 DEVS 모델링 & 시뮬레이션 환경에서 시뮬레이션 모델을 구성하고 Random 스케줄링과 MCT 스케줄링 모델과의 비교 실험을 통하여 제안된 퍼지로직 기반의 그리드 작업 스케줄링 모델이 작업완료시간, 작업손실, 통신량을 개선함으로써 더욱 더 안정적이고 빠른 작업 처리 서비스를 그리드 사용자에게 제공할 수 있다는 사실을 증명하였다.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 1998년도 학술발표회 발표논문집
• /
• pp.22-27
• /
• 1998

A grid-based soil moisture routing model(GRISMORM) was developed to assess the information of groundwater recharge using spatial data such as Landsat TM and digital elevation model etc.. The model predicts the hydrologic components, that is, surface runoff, subsurface runoff, baseflow and evapotranspiration at each grid elements by grid-based water balance computation.

• 품질경영학회지
• /
• 제49권2호
• /
• pp.201-211
• /
• 2021

Purpose: This paper proposes a density adaptive grid algorithm for the k-NN regression model to reduce the computation time for large datasets without significant prediction accuracy loss. Methods: The proposed method utilizes the concept of the grid with centroid to reduce the number of reference data points so that the required computation time is much reduced. Since the grid generation process in this paper is based on quantiles of original variables, the proposed method can fully reflect the density information of the original reference data set. Results: Using five real-life datasets, the proposed k-NN regression model is compared with the original k-NN regression model. The results show that the proposed density adaptive grid-based k-NN regression model is superior to the original k-NN regression in terms of data reduction ratio and time efficiency ratio, and provides a similar prediction error if the appropriate number of grids is selected. Conclusion: The proposed density adaptive grid algorithm for the k-NN regression model is a simple and effective model which can help avoid a large loss of prediction accuracy with faster execution speed and fewer memory requirements during the testing phase.

• 한국산업정보학회논문지
• /
• 제9권1호
• /
• pp.77-84
• /
• 2004

최근, 국내외적으로 국가차원에서 Grid에 대한 다양한 연구가 이루어지고 Grid 컴퓨팅 기술에 대한 상용화의 추세가 보이면서 Grid 시스템에 참여하는 엔티티의 수가 날로 증가하고 있다. 따라서 Globus에 기반 한 Grid환경에서의 기존의 LDAP시스템은 늘어나는 부하를 처리하기에는 충분하지 못하게 되었고 제공할 수 있는 성능의 한계를 초과하고 있다. 이를 위하여 고성능 Grid환경에 부합되는 새로운 LDAP시스템의 설계가 필수적이고 이를 위해서는 기존 LDAP시스템에 대한 성능분석이 우선시 되어야 한다. 하지만 기존의 대부분의 연구는 읽기 동작이 대부분을 차지하는 기존의 응용들을 위한 성능향상에 목적을 두고 있어서 쓰기 동작이 대부분을 차지하는 Grid환경에 적용하기에는 부적합하다. 본 논문에서는 노드수(n), 도착율(λ), 읽기 확률(Pr)변화에 따른 분산 기반 모델과 복제 기반 모델에서 성능분석의 결과를 제시한다. 이를 위하여 M/M/l 큐잉모델을 기초로 기존 LDAP시스템에 대한 분산과 복제에 기반 한 분석모델을 도출하고, 분석모델을 통한 성능분석의 결과를 제시한다. 본 논문의 목표는 이러한 성능분석의 결과를 바탕으로 고성능 Grid환경에 부합되는 새로운 LDAP시스템의 설계방향을 제시하고자 한다. 또한 이러한 결과들은 고성능 Grid환경에서 LDAP기반의 GIS시스템의 설계에 기초자료 활용할 수 있을 것으로 사료된다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2005년도 추계학술대회 및 정기총회
• /
• pp.65-70
• /
• 2005

Recently, Grid is embossed as a new issue according to the need of cooperation related to distributed resources, data sharing, Interaction and so on. It focuses on sharing of large scale resources, high-performance, applications of new paradigms, which improved more than established distributed computing. Because of the environmental specificity distributed geographically and dynamic, the most important problem in grid environment is to share and to allocate distributed grid resources. This paper proposes supply-driven strategies model that is applicable for resource management in grid environment and presents a optimal resource allocation algorithm based on resource demands. Supply-driven strategies model can offer efficient resource management by transaction allocation based on user demand and provider strategy. This paper implements the supply-driven strategies model on the DEVS modeling and simulation environment and shows the efficiency and excellency of this model by comparing with established models.

• 한국시뮬레이션학회논문지
• /
• 제15권3호
• /
• pp.11-21
• /
• 2006

그리드 컴퓨팅의 발전이 증가함에 따라 그리드 자원 관리를 위한 중요성과 필요가 크게 늘어났다. 그러나 지리적으로 분산된 환경에서 자원을 효율적으로 분배하고 활용하는 것은 매우 복잡하다. 이것은 그리드 자원 소유주들이 서로 다른 접근 정책과 제약 조건들을 가지고 있기 때문이다. 사용자들은 그들의 요구에 따라 자원을 요청한다. 그리드 컴퓨팅 시스템의 운영자들은 이러한 요구를 반영하기 위해 시스템 상태를 모니터할 필요가 있다. 그래서 그리드 컴퓨팅 시스템은 자원의 상태를 모니터하는 자원 관리 정책을 필요로 하고 그 자원들을 할당한다. 이 논문은 사용자의 요구와 공급자의 공급 전략에 기반한 거래 할당에 의한 효율적인 자원 관리를 제공하는 사용자 요구 기반 그리드 거래 관리 모델을 제안한다. 성능을 평가하기 위해 이 논문은 자원 거래의 증가율, 거래의 평균 응답 시간, 그리고 처리 시간 활용도를 측정한다. 먼저 거래의 평균 증가율은 경매 모델과 이중 경매 모델보다 각각 585.7%, 322.6% 더 높다. 두 번째로 사용자 요구 기반 그리드 거래 관리 모델의 평균 응답 시간은 3에서 5의 시뮬레이션 시간을 유지한다. 마지막으로, 처리 시간 활용도는 경매 모델과 이중 경매 모델보다 각각 평균 145.4%, 118.0% 더 높다. 이러한 실험 결과는 사용자 요구 기반 그리드 거래관리 모델의 유용성을 입증한다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2007년도 GIS 공동춘계학술대회 논문집
• /
• pp.246-251
• /
• 2007

The purpose of this study is to develop a grid based model for calculating the critical nonpoint source (NPS) pollution load (BOD, TN, TP) in Nak-dong area in South Korea. In the last two decades, NPS pollution has become a topic for research that resulted in the development of numerous modeling techniques. Watershed researchers need to be able to emphasis on the characterization of water quality, including NPS pollution loads estimates. Geographic Information System (GIS) has been designed for the assessment of NPS pollution in a watershed. It uses different data such as DEM, precipitation, stream network, discharge, and land use data sets and utilizes a grid representation of a watershed for the approximation of average annual pollution loads and concentrations. The difficulty in traditional NPS modeling is the problem of identifying sources and quantifying the loads. This research is intended to investigate the correlation of NPS pollution concentrations with land uses in a watershed by calculating Expected Mean Concentrations (EMC). This work was accomplished using a grid based modelling technique that encompasses three stages. The first step includes estimating runoff grid by means of the precipitation grid and runoff coefficient. The second step is deriving the gird based model for calculating NPS pollution loads. The last step is validating the gird based model with traditional pollution loads calculation by applying statistical t-test method. The results on real data, illustrate the merits of the grid based modelling approach. Therefore, this model investigates a method of estimating and simulating point loads along with the spatially distributed NPS pollution loads. The pollutant concentration from local runoff is supposed to be directly related to land use in the region and is not considered to vary from event to event or within areas of similar land uses. By consideration of this point, it is anticipated that a single mean estimated pollutant concentration is assigned to all land uses rather than taking into account unique concentrations for different soil types, crops, and so on.