By Topic

Adaptive staircase multiple failure detector for parallel and distributed image processing

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Bansal, S. ; Acropolis Inst. of Technol. & Res., Indore, India ; Sharma, S. ; Trivedi, I.

Failure of multiple nodes detection is a complex task in parallel and collaborative image processing on a cluster. Adaptive heartbeat detectors with complex prediction system are not effective due to high overheads as image processing itself having high time complexity and thus make such detectors unrealistic. In this paper an improved algorithm is proposed which combine stair case heartbeat mechanism with adaptive automatic time predication mechanism for such image processing application. All nodes are broadcasting with “I am ok” message by setting the time initially min time. All nodes who answer are kept in a first working node list. Again time is increased in stair case manner for only those nodes who had not answered. This is repeated till maximum time is reached. After this, node is declared as a faulty node if it does not answer. It improves the accuracy of the multiple failure detectors since this algorithm relates the time of different node as per the load and traffic by gradually determined stair case intervals. It is simple since no complex and time-consuming time prediction mechanism is incorporated. Simulation Results presented validate the effectiveness of the proposed algorithm.

Published in:

Recent Advances in Information Technology (RAIT), 2012 1st International Conference on

Date of Conference:

15-17 March 2012