基于MapReduce的并行石漠化CA模型  

Parallel rocky desertification CA model based on MapReduce

作　　者：张学锋[1] 余利[1] 胡宝清[2] 严国全[1] 李博[1] 

机构地区：[1]安徽工业大学计算机学院,安徽马鞍山243032 [2]广西师范学院资源与环境科学学院,南宁530001

出　　处：《计算机工程与应用》2013年第16期40-42,46,共4页Computer Engineering and Applications

基　　金：国家自然科学基金项目(No.40871250);广西北部湾重大专项(No.2011GXNSFE018003);广西新世纪十百千人才工程第二层次专项(No.2007224);安徽省高校省级优秀青年人才基金(No.2010SQRL039)

摘　　要：针对石漠化演化模拟预测CA模型在单机上训练和运行时间较长的问题。给出了MapReduce编程模型实现的并行化石漠化CA模型,并在用普通PC搭建的Hadoop集群上进行研究实验。实验结果表明,在Hadoop集群上实现的MapReduce并行化石漠化CA模型具有较好的加速比。According to the problem that the CA model of rocky desertification evolution simulation and prediction runs in a sin- gle PC has a long time. This paper gives a parallel rocky desertification CA model based on MapReduce programming model, and performs research test in a Hadoop cluster built by the ordinary PC, the experimental results show that the parallel MapRe- duce rocky desertification CA model implemented in the Hadoop group has better speedup.

关 键 词：云计算 并行计算 MAPREDUCE模型 CA模型 石漠化 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]