Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2012, Vol. 38 ›› Issue (11): 27-29,37. doi: 10.3969/j.issn.1000-3428.2012.11.009

Special Issue:

• Networks and Communications • Previous Articles     Next Articles

Improved Map-Reduce Model in Cloud Computing Environment

LI Zhen, DU Zhong-jun   

  1. (College of Computer Science, Sichuan University, Chengdu 610065, China)
  • Received:2011-08-15 Online:2012-06-05 Published:2012-06-05

云计算环境下的改进型Map-Reduce模型

李 震,杜中军   

  1. (四川大学计算机学院,成都 610065)
  • 作者简介:李 震(1986-),男,硕士研究生,主研方向:云计算,数据库系统;杜中军,副教授

Abstract: Map-Reduce model does not consider the computing performance in large number of heterogeneous nodes when allocating the input files in the cluster, and this leads to network data transfer increase to run the map task. Addressing this issue, this paper proposes the improved Map-Reduce model under the cloud computing environment. For a large number of nodes in the cluster calculation with different performance, it raises the maximum computational time minimal objective function model, uses Genetic Algorithm(GA) to solve the model to get the distribution plan. Simulation results prove the validity of the model.

Key words: cloud computing, Map-Reduce model, heterogeneous environment, calculated performance, Genetic Algorithm(GA)

摘要: Map-Reduce模型在分配输入文件时没有考虑集群中大量异构节点的计算性能,导致运行map任务时网络数据传送量增加。针对该问题,提出一种云计算环境下的改进型Map-Reduce模型。根据集群中大量节点计算性能不同的特点,采用最小化最大计算时间的目标函数进行建模,利用遗传算法求解该模型得到分配方案。仿真结果证明了该模型的有效性。

关键词: 云计算, Map-Reduce模型, 异构环境, 计算性能, 遗传算法

CLC Number: