Cloud-based Image Processing System with Priority-based Data Distribution Mechanism

doi:10.1016/j.comcom.2012.06.015

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Journal Article > Item 987654321/92165

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/92165

Title:	Cloud-based Image Processing System with Priority-based Data Distribution Mechanism
Authors:	Wu, Tin-Yu;Chen, Chi-Yua;Kuo, Ling-Shang;Lee, Wei-Tsong;Chao, Han-Chieh
Contributors:	淡江大學電機工程學系
Keywords:	3D image;Cloud system;Multicast streaming;Image processing
Date:	2012-09-01
Issue Date:	2013-09-12 13:01:52 (UTC+8)
Publisher:	Amsterdam: Elsevier BV
Abstract:	Most users process short tasks using MapReduce. In other words, most tasks handled by the Map and Reduce functions require low response time. Currently, quite few users use MapReduce for 2D to 3D image processing, which is highly complicated and requires long execution time. However, in our opinion, MapReduce is exactly suitable for processing applications of high complexity and high computation. This paper implements MapReduce on an integrated 2D to 3D multi-user system, in which Map is responsible for image processing procedures of high complexity and high computation, and Reduce is responsible for integrating the intermediate data processed by Map for the final output. Different from short tasks, when several users compete simultaneously to acquire data from MapReduce for 2D to 3D applications, data that waits to be processed by Map will be delayed by the current user and Reduce has to wait until the completion of all Map tasks to generate the final result. Therefore, a novel scheduling scheme, Dynamic Switch of Reduce Function (DSRF) Algorithm, is proposed in this paper for MapReduce to switch dynamically to the next task according to the achieved percentage of tasks and reduce the idle time of Reduce. By using Hadoop to implement our MapReduce platform, we compare the performance of traditional Hadoop with our proposed scheme. The experimental results reveal that our proposed scheduling scheme efficiently enhances MapReduce performance in running 2D to 3D applications.
Relation:	Computer Communications 35(15), pp.1809–1818
DOI:	10.1016/j.comcom.2012.06.015
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
Cloud-based image processing system with priority-based data.pdf		1243Kb	Adobe PDF	732	View/Open
index.html		0Kb	HTML	272	View/Open

Loading...