• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.507-516
• /
• 2013

Mobile devices have limited computing power and resources. Since mobile devices are equipped with rich network connectivity, an approach to subscribe cloud services can effectively remedy the problem, which is called Mobile Cloud Computing (MCC). Most works on MCC depend on a method to offload functional components at runtime. However, these works only consider the limited verion of offloading to a pre-defined, designated node. Moveover, there is the limitation of managing services subscribed by applications. To provide a comprehensive and practical solution for MCC, in this paper, we propose a self-stabilizing process and its management-related methods. The proposed process is based on an autonomic computing paradigm and works with diverse quality remedy actions such as migration or replicating services. And, we devise a pratical offloading mechanism which is still in an initial stage of the study. The proposed offloading mechanism is based on our proposed MCC meta-model. By adopting the self-stabilization process for MCC, many of the technical issues are effectively resolved, and mobile cloud environments can maintain consistent levels of quality in autonomous manner.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.1
• /
• pp.343-364
• /
• 2021

In this study, as examples of domestic libraries currently using the cloud-based library system, the main characteristics and issues that appeared in the experience of use divided into the processes of introduction, conversion, and operation of each system were investigated, and the results are as follows. First, it is said that new systems were introduced as alternatives to problems caused by the operation of the existing system, and the current products were selected because they were cost-effective. Second, the main issues in the conversion process were data migration work, implementation of existing service functions, and linking problems of internal and external systems in the library. Third, the main advantages identified in the operation process were cost reduction, simple installation and automatic management and maintenance, and convenient use in mobile devices. The main drawbacks were the difficulty of customizing that reflects the characteristics of the library, and the need for stability of the network. The disappeared role of the information technology librarian is the regular system inspection and maintenance support, and various new roles have been suggested. The responses of librarians and users to the new system were generally satisfied rather than dissatisfied.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.17-20
• /
• 2017

실시간 마이그레이션은 데이터 센터 내에서 자원을 효율적으로 관리할 수 있도록 하는 기술이다. 그러나 대부분의 연구는 마이그레이션 Metric간 Trade-off를 고려하고 있지 않아 Qos저하의 우려가 있기 때문에 서비스 목적에 따라 다수의 Metric을 고려해야한다. 마이그레이션 시 고려되는 요소들을 분류하고 이를 복합적으로 고려할 수 있는 퍼지이론 기반의 마이그레이션 기법을 제시하고자 한다. 또한 향후 연구에 대해서도 논의한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.45-48
• /
• 2015

클라우드 시스템은 IaaS를 제공하기 위한 핵심기술 이다. 고사양의 자원을 서비스의 형태로 제공 하면서 사용자에게 편의성을 제공하며 사용자들의 개인용 컴퓨터를 더욱더 편하게 사용 할 수 있게끔 한다. 하지만 서비스가 증대됨에 따라 서버의 자원을 관리하는 기술의 중요성도 증가되고 있다. 본 논문에서는 클라우드 서버 자원들의 상태를 모니터링 하여 서버 과부하나 성능저하의 원인을 알아내고, 동적 페이지 마이그레이션을 수행하여 사용자의 불편을 최소로 하는 마이그레이션 구조를 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.155-157
• /
• 2013

클라우드 컴퓨팅은 가상화를 통하여 자원을 효율적으로 이용하며, 전체 시스템의 성능 개선을 위해 부하가 심한 물리 서버의 가상 머신을 마이그레이션한다. 클라우드 컴퓨팅의 규모가 커짐에 따라 부하 분산을 통한 효율적 자원 관리는 더욱 중요해지고 있다. 본 논문에서는 가상 머신 부하 분산 기술의 동향에 대해서 조사한다.

• Journal of Korean Society of Archives and Records Management
• /
• v.16 no.4
• /
• pp.79-120
• /
• 2016

Along with the changing computing environment, the production of public documents is moving to G-Cloud and On-nara System, which are re-engineered on G-Cloud. In this process, it is predicted that the Open Document Format (ODF) will replace the proprietary document format, HWP, and will become widely used in the near future. To preserve digital records produced in ODF, this study reviewed the current long-term preservation strategies and identified considerations for new formats. For ODF source files, it is suggested to eliminate the conversion to PDF/A-1 and preserve the documents in the extended ODF with added metadata of records management. Moreover, ODF is presented as an alternative format for preserving proprietary formats. Finally, this study reviewed the current long-term preservation format, i.e., NEO, and suggests a zipped BagIt package, which has an ISO 21320 specification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4103-4121
• /
• 2018

Quality of Service (QoS) awareness is recognized as a key point for the success of Internet of Things (IOT).Realizing the full potential of the Internet of Things requires, a real-time task scheduling algorithm must be designed to meet the QoS need. In order to schedule tasks with diverse QoS requirements in cloud environment efficiently, we propose a task scheduling strategy based on dynamic priority and load balancing (DPLB) in this paper. The dynamic priority consisted of task value density and the urgency of the task execution, the priority is increased over time to insure that each task can be implemented in time. The scheduling decision variable is composed of time attractiveness considered earliest completion time (ECT) and load brightness considered load status information which by obtain from each virtual machine by topic-based publish/subscribe mechanism. Then sorting tasks by priority and first schedule the task with highest priority to the virtual machine in feasible VMs group which satisfy the QoS requirements of task with maximal. Finally, after this patch tasks are scheduled over, the task migration manager will start work to reduce the load balancing degree.The experimental results show that, compared with the Min-Min, Max-Min, WRR, GAs, and HBB-LB algorithm, the DPLB is more effective, it reduces the Makespan, balances the load of VMs, augments the success completed ratio of tasks before deadline and raises the profit of cloud service per second.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.25-28
• /
• 2011

최근 사이언스 컴퓨팅 분야에서 대용량 데이터가 발생하고 있고 컴퓨팅 자원들의 수요도 급증하고 있다. 이로 인해 클라우드 컴퓨팅 기술의 필요성이 중요시되고 있고 전 세계적으로 급속히 발전하고 있다. 천문 연구 분야에서 관측기기의 발전으로 대용량의 천문 데이터가 생산되고 있다. 이를 처리하기 위하여 다양한 클라우드 컴퓨팅 기술을 이용한 데이터 분석 환경이 요구되고 있다. 이러한 환경을 구축하기 위해서는 가상 인프라 자원을 효율적으로 관리할 수 있어야 한다. 현재 가상 인프라 자원을 관리하기 위해 오픈 소스를 개발하는 프로젝트들이 활발히 진행되고 있다. 본 논문에서는 오픈 소스인 Eucalyptus와 OpenNebula의 기능적인 측면을 크게 10가지로 분류하여 장단점을 비교 분석하였고 OpenNebula의 세 가지 특징인 중앙 집중화된 구조, live migration과 suspend/resume 기능, 커스터마이징 기능이 대용량 천문 응용 수행을 위한 환경을 구축하는데 반드시 필요하기 때문에 OpenNebula를 채택하였다. OpenNebula를 사용해 구축한 사이언스 클라우드 테스트베드는 NFS 서버의 별도 구성을 통한 성능 개선, 하이브리드 클라우드 컴퓨팅 환경 구축, B클래스 사설 네트워크 구성, GUI 기반 사이언스 클라우드 테스트베드 관리 및 모니터링 기능의 4가지 특징을 가지고 있다. 앞으로도 천문 연구자들에게 안정적인 서비스를 제공하기 위하여 관련 연구를 계속할 것이다.

• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.473-478
• /
• 2016

Server virtualization provides abstraction of physical resources to users and thus accomplishes high resource utilization and flexibility. However, the characteristics of server virtualization, such as the limited number of physical resources shared by virtual machines, can cause problems, mainly performance interference. The performance interference is caused by the fact that the CPU scheduler running on the host operating system schedules virtual machines without considering the characteristics of the virtual machine's internal process. To address performance interference, a number of research activities to improve performance interference have been conducted, but do not deal with the fundamental analysis of performance interference. In this paper, in order to analyze the cause of performance interference, we carry out profiling in a variety of scenarios in a virtualized environment based on KVM. As a result, we analyze the phenomenon of the performance interference in terms of CPU scheduling and propose an efficient scheduling solution.