摘要
数据密集型应用越来越多,如何将大数据在数据中心实现有效放置变得日益重要。研究了大数据的放置模型。影响大数据放置的因素主要有:能耗、异构节点的服务能力及具有关联计算的数据集。基于这3个因素设计了一种节能、充分考虑异构节点服务能力及提升MapReduce处理Join连接的效率的大数据放置模型。该模型将有效实现大数据的有效放置管理,同时也为未来软件定制数据中心奠定了基础。
More and more data-intensive applications have come into being.It is becoming more and more important for the big data＇ efficient placement in the data center.This paper proposed a kind of big data placement model.The major factors that influce the big data placement have the following three points：energy consumption,sevice capability of heterogeneous node and the data sets which have associated computing.Based on these three factors,our big data placement model considers the energy-saving,service capability of heterogeneous node and the complex Join query mapreduce computing so on.This model can implement the big data＇s efficient placement management efficiently.At the same time,it will estabilish a foundation for software customized data center in the future.
出处
《计算机科学》
CSCD
北大核心
2014年第6期1-4,36,共5页
Computer Science
基金
高等学校博士学科点专项科研基金课题(20100002110082)资助
关键词
大数据
数据放置
节能
异构节点
关联计算
Big data
Data placement
Energy-saving
Heterogeneous nodes
Associated computing
