2012 | OriginalPaper | Chapter
Applying MapReduce Framework to Peer-to-Peer Computing Applications
Authors : Huynh Tu Dang, Ha Manh Tran, Phach Ngoc Vu, An Truong Nguyen
Published in: Computational Collective Intelligence. Technologies and Applications
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
MapReduce is a programming framework for processing large amount of data in distribution. MapReduce implementations, such as Hadoop MapReduce, basically operate on dedicated clusters of workstations to achieve high performance. However, the dedicated clusters can be unrealistic for users who infrequently have a demand of solving large distributed problems. This paper presents an approach of applying the MapReduce framework on peer-to-peer (P2P) networks for distributed applications. This approach aims at exploiting leisure resources including storage, bandwidth and processing power on peers to perform MapReduce operations. The paper also introduces a prototyping implementation of a MapReduce P2P system, where the main functions of peers contain contributing computing resources, forming computing groups and executing the MapReduce operations. The performance evaluation of the system has been compared with the Hadoop cluster using the prevailing word count problem.