Improved Map-Reduce Model in Cloud Computing Environment
DU Zhong-jun · Jisuanji gongcheng · 2012
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.