• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.1691-1693
• /
• 2010

본 논문에서는 OpenNebula 기반의 클라우드 컴퓨팅 환경을 구축하고 클러스터 노드에 설치되는 하이퍼바이저로 Xen을 이용하여 클라우드 컴퓨팅 기반 컴퓨터 교육 시스템을 구축하였다. 전체 시스템은 Front-End 1대와 클러스터 노드 2대로 구성되며, 시스템 사용자는 원격 접속을 이용하여 가상 머신에 접근이 가능하다. 관리자는 Web를 통해 클러스터 노드와 가상 머신을 관리할 수 있으며, 컴퓨터 실습수업의 형태에 따라 각기 다른 OS와 응용 소프트웨어가 설치된 가상머신을 생성하여 사용자들에게 제공할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.351-354
• /
• 2012

The core of cloud computing is to provide efficient computing resource sharing. In this paper, we have designed and implemented a virtual computer lab system using open source cloud computing infrastructure. The proposed virtual computer lab system can be used to reduce computer upgrade and maintenance cost significantly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.906-908
• /
• 2010

클라우드 컴퓨팅 환경을 구축할 수 있게 하는 OpenNebula는 ONE 스케줄러를 통해 가상머신들의 라이프 사이클을 관리한다. ONE 스케줄러는 가상머신을 할당 할 때, 클러스터 노드의 물리적 자원 할당 여부만을 고려하기 때문에 가상 머신 생성 후의 부하를 예측하기 힘들다. 본 논문에서는 사용자의 이전 가상 머신 사용 패턴을 기반으로 부하 등급을 나누고 이 등급에 따라 가상머신을 동적으로 할당하는 기법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.125-126
• /
• 2009

본 논문에서는 클라우드 컴퓨팅 기반의 가상머신 임대 서비스 구현을 위해 OpenNebula 기반의 클라우드 클러스터를 구축하였다. 클라우드 클러스터는 1대의 Front-End와 4대의 클러스터 노드로 구성하고 클러스터 노드에는 Xen을 통하여 서버 가상화를 실현한다. 사용자는 개인 맞춤형 가상머신 요구사항 템플릿을 작성한 뒤 Front-End를 통하여 클라우드 클러스터에 가상 머신 임대 서비스를 요청한다. 본 실험에서 총18개의 가상머신을 임대하는 서비스를 실행하여 생성된 가상 머신의 동작 및 네트워크 서비스를 구현하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.213-221
• /
• 2012

In this paper, a dynamic power management system is proposed to reduce energy consumption for multiple clients in cloud computing environments. The proposed system monitors both keyboard and mouse input from the user, available memory, and CPU usage in the virtual machine. If the system detects no keyboard and mouse input for a certain amount of time and both available memory and CPU usage reach predefined threshold value, the manager in the virtual machine orders the client to shutdown the client machine, which results in significant power save. The developed system is applied to the real university computer lab and the performance of the system is evaluated.

• Journal of The Korean Astronomical Society
• /
• v.37 no.4
• /
• pp.285-288
• /
• 2004

Near-infrared imaging photometry supplemented by optical spectroscopy and narrow-band imaging of the H II region Sh 2-128 and its environment are presented. This region contains a developed H II region and the neighboring compact H II region S 128N associated with a pair of water maser sources. Midway between these, the core of a CO cloud is located. The principal ionizing source of Sh 2-128 is an 07 star close to its center. A new spectroscopic distance of 9.4 kpc is derived, very similar to the kinematic distance to the nebula. This implies a galactocentric distance of 13.5 kpc and z = 550 pc. The region is optically thin with abundances close to those predicted by galactocentric gradients. The $JHK_s$ images show that S 128N contains several infrared point sources and nebular emission knots with large near-infrared excesses. One of the three red Ks knots coincides with the compact H II region. A few of the infrared-excess objects are close to known mid- and far-infrared emission peaks. Star counts in J and $K_s$ show the presence of a small cluster of B-type stars, mainly associated with S 128N. The $JHK_s$ photometric properties together with the characteristics of the other objects in the vicinity suggest that Sh 2-128 and S 128N constitute a single complex formed from the same molecular cloud, with ages ${\~}10^6$ and < $3 {\times} 10^5$ years respectively. No molecular hydrogen emission was detected at 2.12 ${\mu}m$. The origin of this remote star forming region is an open problem.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.3
• /
• pp.567-575
• /
• 2011

The two most popular virtual machine allocation schemes, both match making and round robin, do consider hardware specifications such as CPU, RAM, and HDD, but not CPU usage, which results in balanced resource distribution, but not in balanced resource usage. Thus, in this paper a new virtual machine allocation scheme considering current CPU usage rate is proposed while retaining even distribution of node resources. In order to evaluate the performance of the proposed scheme, a cloud computing platform composed of three cloud nodes and one front end is implemented. The proposed allocation scheme was compared with both match making and round robin schemes. Experimental results show that the proposed scheme performs better in even distribution of overall CPU usage, which results in efficient load balancing.