지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 이봉환
- 발행연도
- 2013
- 저작권
- 대전대학교 논문은 저작권에 의해 보호받습니다.
이용수0
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Cloud computing is regarded as an emerging technology and commercial cloud services are becoming widely spreaded. In this thesis, a virtual computing lab environment is implemented for VDI service using open source cloud computing platform and a node power scheduler is proposed in order to reduce power consumption on data nodes in cloud server farm. The proposed power manager stops operation of end nodes when they are not in service and resumes operation when virtual machine needs to be active again. In order to implement the power manager, both WOL (Wake-on-LAN) and SSH (secure shell) are used.
The implemented virtual computing lab system is composed of one head node, four end nodes, and two data nodes. A desktop version OS is installed on the head node and 30 virtual machines are created on four end nodes. The performance of the proposed power manager is evaluated. The power consumption on the data nodes are compared in case of with and without the power scheduler. Power consumption is measured three times to provide reliability for each case. The experimental results show that the total power consumption with the proposed power manager on the four data nodes are decreased by 40%. In conclusion, the proposed power managing scheduler can be very useful to reduce power consumption in virtual computing lab environments.
The implemented virtual computing lab system is composed of one head node, four end nodes, and two data nodes. A desktop version OS is installed on the head node and 30 virtual machines are created on four end nodes. The performance of the proposed power manager is evaluated. The power consumption on the data nodes are compared in case of with and without the power scheduler. Power consumption is measured three times to provide reliability for each case. The experimental results show that the total power consumption with the proposed power manager on the four data nodes are decreased by 40%. In conclusion, the proposed power managing scheduler can be very useful to reduce power consumption in virtual computing lab environments.
목차
등록된 정보가 없습니다.
최근 본 자료
댓글(0)
0