• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제12권5호
• /
• pp.275-285
• /
• 2006

본 논문에서는 그리드 컴퓨팅의 기존 자원 거래망 모델들의 문제점을 분석하고, 해결하기 위한 새로운 자원 거래 모델을 제안한다. 이 모델은 사용자와 자원 공급자 사이의 거래 가격을 예측하고 합리적인 거래 가격을 제시한다. 합리적인 가격 제안을 통해, 사용자와 자원 공급자 사이의 더 많은 자원 거래를 발생시키고, 사용자는 더 짧은 시간에 자원을 공급받게 된다. 본 논문에서 사용자의 자원 요구량 예측 정확도를 향상시키기 위하여 통계학의 예측 모델을 도입하였고 합리적인 가격 제안을 위해 미시 경제학의 가격 결정 이론을 도입하였다. 본 모델의 성능 평가를 위하여 사용자의 자원 요구량 예측 정확도, 자원 거래를 위한 응답시간, 자원 거래 횟수 그리고 사용자의 자원 활용률을 측정하였다. 실험의 결과로는 자원 예측 정확도는 87.45%의 신뢰성 있는 결과를 얻었고, 기존 모델들에 비해 응답시간은 72.39% 단축 되었다. 또한, 자원 거래 횟수는 162.56% 증가 하였다. 본 논문에서 제안하는 모델의 평균 자원 활용률은 90%에 근접했으며 기존 모델들과 비교해서는 230%이상 자원 활용률이 증가 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권10호
• /
• pp.1712-1732
• /
• 2011

Cloud provides dynamically scalable virtualized computing resources as a service over the Internet. To achieve higher resource utilization over virtualization technology, an optimized strategy that deploys virtual machines on physical machines is needed. That is, the total number of active physical host nodes should be dynamically changed to correspond to their resource usage rate, thereby maintaining optimum utilization of physical machines. In this paper, we propose a pattern-based prediction model for resource provisioning which facilitates best possible resource preparation by analyzing the resource utilization and deriving resource usage patterns. The focus of our work is on predicting future resource requests by optimized dynamic resource management strategy that is applied to a virtualized data center in a Cloud computing environment. To this end, we build a prediction model that is based on user request patterns and make a prediction of system behavior for the near future. As a result, this model can save time for predicting the needed resource amount and reduce the possibility of resource overuse. In addition, we studied the performance of our proposed model comparing with conventional resource provisioning models under various Cloud execution conditions. The experimental results showed that our pattern-based prediction model gives significant benefits over conventional models.

• 한국시뮬레이션학회논문지
• /
• 제15권4호
• /
• pp.129-136
• /
• 2006

그리드 컴퓨팅은 단일 컴퓨터로는 해결할 수 없는 대용량의 작업을 처리하기 위해 제안되었다. 그리드 컴퓨팅은 지리적으로 분산된 이기종 자원들을 상호 연결하여 대용량의 작업들을 처리하는 새로운 차세대 컴퓨팅이다. 그런데, 분산된 이기종의 자원들을 모을 때에 많은 어려운 문제들이 발생한다. 특히, 자원들의 신뢰성을 보장하는 것은 가장 심각한 문제 중에 하나이다. 그래서 우리는 그리드 자원의 신뢰성을 측정하여 자원을 할당하는 그리드 자원 신뢰성 측정 스케줄링 모델을 제안한다. 우리는 자원의 상태 정보를 기반으로 하여 자원 신뢰성을 측정하고, DEVSJAVA 모델링과 시뮬레이션 환경에서 그리드 시뮬레이션 모델에 그리드 자원 신뢰성 측정 방법을 적용하였다. 그리고, 이 논문은 스케줄링 모델들의 Utilization, Job loss, Throughput 그리고 Average Turn-around Time 같은 파라미터들을 측정하였고, 자원 신뢰성 측정을 이용한 그리드 자원 신뢰성 측정 스케줄링 모델의 실험 결과들을 기존의 스케줄링 모델들(랜덤 스케줄링 모델, 라운드 로빈 스케줄링 모델)과 비교하였다. 이 실험 결과들은 자원 신뢰성 측정 스케줄링 모델이 랜덤 스케줄링 모델과 라운드 로빈 스케줄링 모델에 비해 효율적인 자원 할당과 안정적인 작업 처리를 제공한다는 것을 보여준다.

• 한국컴퓨터정보학회논문지
• /
• 제23권4호
• /
• pp.107-114
• /
• 2018

Recently, various wearable personal devices such as a smart watch have been developed and these personal devices are being miniaturized. The user desires to receive new services from personal devices as well as services that have been received from personal computers, anytime and anywhere. However, miniaturization of devices involves constraints on resources such as limited input and output and insufficient power. In order to solve these resource constraints, this paper proposes a resource collaboration system which provides a service by composing sharable resources in the resource sharing environment like IoT. the paper also propose a method to infer and recommend user-customized resources among various sharable resources. For this purpose, the paper defines an ontology for resource inference. This paper also classifies users behavior types based on a user model and then uses them for resource recommendation. The paper implements the proposed method as a prototype system on a personal device with limited resources developed for resource collaboration and shows the effectiveness of the proposed method by evaluating user satisfaction.

• 디지털콘텐츠학회 논문지
• /
• 제2권2호
• /
• pp.167-178
• /
• 2001

고성능 그리드 환경을 구축을 위해서는 그리드 내의 사용자, 관리자, 서비스, 하드웨어 등에 대한 제반 정보서비스를 제공하는 그리드 정보서비스(Grid Information Service)가 필수적으로 요구된다. 본 논문에서는 그리드 정보서비스의 구조(Grid Information Service Architecture) 설계에 근간이 되는 자원정보 모델(Resource Information Model)에 대하여 체계적인 연구를 수행하였다. 본 연구는 자원요청 자원탐색, 자원할당 등 자원 스케줄링의 최적화 알고리즘의 개발 및 구현을 보장할 수 있는 자원정보모델의 성격 및 특성에 대한 요구정의(Requirement Definition)의 도출에 초점을 두었다. 본 고에서는 고성능 그리드 정보서비스(GIS)는 엔티티기술(Entity Description)과 자원 상호 간의 관계기술(Relation Description)을 포함한 자원기술(Resource Description), 스케줄링 지원, 자원정보 표현모델과 저장 모델의 독립성 사용자 측면의 자원기술방식과 시스템 측면의 자원기술방식의 분리에 대한 이슈가 명확하게 반영된 자원정보모델을 기반으로 하여 설계되어야 한다는 점을 명확히 제시한다. 이러한 자원정보모델에 준하여 기존의 대표적인 자원정보모델들을 분석한 후 그 결과를 기술한다.

• Asian Journal of Business Environment
• /
• 제4권4호
• /
• pp.5-11
• /
• 2014

Purpose - The paper aims to study strategic enterprise resource initiative formation processes. It analyzes the process of managing the strategic resource initiative and discusses its implementation mechanism. A research model for enterprises' strategic development is proposed, which suggests a geometric interpretation for estimating a company's long-term development. Research design, data, and methodology - The analysis employs theoretical studies of modern researchers. The main models used to determine the optimal alternative business strategy are graphic interpretation and mathematical modeling. Results - The hypotheses testing demonstrates the definition of a company's strategic resource initiative and explains the-mechanism or design of its formation. The study presents a geometric prism-refraction model of practice using a strategic resource initiative. Conclusions - An enterprise's strategy could return to its initial state in case of its unexpected deviation as a result of passing through the nodal points. The proposed model allows us to evaluate business performance, its surrounding environment, and the resource management strategy, to determine the necessary scope of strategy changes necessary to bring it back to the original state.

• 한국시스템다이내믹스연구
• /
• 제7권1호
• /
• pp.67-90
• /
• 2006

A series of system dynamics model was developed for forecasting demand and supply of human resource in the electricity industry. To forecast demand of human resource in the electric power industry, BLS (Bureau of Labor Statistics) methodology was used. To forecast supply of human resource in the electric power industry, forecasting on the population of our country and the number of students in the department of electrical engineering were performed. After performing computer simulation with developed system dynamics model, it is discovered that the shortage of human resource in the electric power industry will be 3,000 persons per year from 2006 to 2015, and more than a double of current budget is required to overcome this shortage of human resource.

• 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.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2005년도 추계학술대회 및 정기총회
• /
• pp.45-50
• /
• 2005

Research and development of grid computing ware mainly focused on high performance computing field such as large-scale computing operation. Many companies and organizations concentrated on existing computational grid. However, service grid focusing on enterprise environments has been noticed gradually. Grid service providers of service grid construct diverse and specialized services and provide service resources that have economic feasibility to grid users. But, service resources are geographically dispersed and divided into many classes and have individual owners and management policies. In order to utilize and allocate resources effectively, service grid needs a resource management model that handles and manages heterogeneous resources of service grid. Therefore, this paper presents the third party grid service marketplace model using virtualization to solve problems of grid service resource management. Also, this paper proposes resource dealing mechanism and pricing algorithms applicable for service grid. Empirical results show usefulness and efficiency of the third party grid service marketplace model in comparison with typical economic models for grid resource management such as single auction model and double auction model.

• Journal of Information Processing Systems
• /
• 제14권2호
• /
• pp.377-395
• /
• 2018

Aiming at the problem of service reliability in resource reservation in cloud computing environments, a model of dynamic cloud resource reservation based on trust is proposed. A domain-specific cloud management architecture is designed in which resources are divided into different management domains according to the types of service for easier management. A dynamic resource reservation mechanism (DRRM) is used to test users' reservation requests and reserve resources for users. According to user preference, several resources are chosen to be candidate resources by fuzzy cluster analysis. The fuzzy evaluation method and a two-way trust evaluation mechanism are adopted to improve the availability and credibility of the model. An analysis and simulation experiments show that this model can increase the flexibility of resource reservation and improve user satisfaction.