云计算数据中心光互连网络:研究现状与趋势  被引量:26

The Optical Interconnection Network for Cloud Computing Data Centers:State of the Art and Future Research

在线阅读下载全文

作  者:余晓杉[1] 王琨[2] 顾华玺[1] 王曦[1] 

机构地区:[1]西安电子科技大学ISN国家重点实验室,西安710071 [2]西安电子科技大学计算机学院,西安710071

出  处:《计算机学报》2015年第10期1924-1945,共22页Chinese Journal of Computers

基  金:国家自然科学基金(61472300);中央高校基本业务经费(JB150318;JB142001-5);高等学校学科创新引智计划(B08038)资助~~

摘  要:数据中心是云计算的核心支持平台,云计算的发展对数据中心网络架构提出了严峻的挑战,传统电互连网络架构难以在带宽、设备开销、能耗、管理复杂度等方面同时满足云应用的要求,因此以低能耗、低开销、高带宽为特点的光互连网络架构出现并受到研究人员的广泛关注.该文在对比电互连技术和光互连技术基本特点的基础上,对数据中心光互连网络的研究现状展开综述,具体介绍了现有的光电混合网络、集中式全光网络和分布式全光网络,并从交换机制、扩展性、技术可行性、设备开销等方面对上述网络架构进行了对比分析.最后该文对数据中心光互连网络的未来研究趋势进行了总结和展望.Data center is the key platform to support cloud computing.The rapid development of cloud-based services and applications has brought great challenges to data center network.Traditional electronic interconnection network can hardly satisfy all requirements for bandwidth,cost of devices,power consumption,and management.The optical interconnection network,which is characterized by low power consumption,low cost and high bandwidth,is proposed to solve this problem.Recently it has become a hot topic in the field of research.Based on the comparison of the basic characteristics of the optical and electronic interconnection techniques,this paper presents a survey on the research progress of the optical interconnects for cloud computing data center.The proposed optical interconnect schemes include the optical/electronic hybrid networks,the centralized all-optical networks,and the distributed all-optical networks.We analyze and compare these optical interconnects in terms of the switching strategy,scalability,technical feasibility,equipment cost,and so on.Finally,this paper proposes some future research topics in the optical data center network for cloud computing.

关 键 词:云计算 数据中心网络 光互连技术 

分 类 号:TP393[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象