Effective Reduction of Network Traffic Cost in Map Reduce for Very Large Scale Data Applications

JCOM_V4_N4_RP2 Effective Reduction of Network Traffic Cost in Map Reduce for Very Large Scale Data Applications K. Reddamma D. Jagadeesan T. Vivekanandan Journal on Computer Science 2347–6141 4 4 14 19 Aggregator, Big Data, Hadoop, Hash Table, MapReduce, Optimistic Distributed Algorithm The MapReduce programming model provides an exciting opportunity to process massive volumes of heterogeneous data using map and reduce tasks in parallel. In the recent time, a number of efforts has been made to improve the performance of the job’s execution. The performance of the job’s execution can be improved further by considering the network traffic. In this paper, an optimistic distributed algorithm is proposed to deal with the significant optimization problem for handling large size data. The optimistic distributed algorithm is more efficient than the distributed algorithm. Finally, simulation results show that the proposal can significantly reduce network traffic cost. December 2016 - February 2017 Copyright © 2017 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=13415