DSpace@nitr >
National Institue of Technology- Rourkela >
Thesis (MTech by Research) >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/667

Full metadata record

DC FieldValueLanguage
contributor.authorEkka, A A-
contributor.authorSahoo, Bibhudatta (Guide)-
date.accessioned2008-04-24T06:42:54Z-
date.available2008-04-24T06:42:54Z-
date.issued2007-
identifier.citationFault Tolerant Real Time Dynamic Scheduling Algorithm For Heterogeneous Distributed System, Thesis submitted in partial fulfillment of the requirements for the award of the Master of Technology by Research in Computer Science, to National Institute of Technology, Rourkelaen
identifier.urihttp://hdl.handle.net/2080/667-
descriptionCopyright for the thesis belongs to National Institute of Technology Rourkelaen
description.abstractFault-tolerance becomes an important key to establish dependability in Real Time Distributed Systems (RTDS). In fault-tolerant Real Time Distributed systems, detection of fault and its recovery should be executed in timely manner so that in spite of fault occurrences the intended output of real-time computations always take place on time. Hardware and software redundancy are well-known e ective methods for faulttolerance, where extra hard ware (e.g., processors, communication links) and software (e.g., tasks, messages) are added into the system to deal with faults. Performances of RTDS are mostly guided by eciency of scheduling algorithm and schedulability analysis are performed on the system to ensure the timing constrains. This thesis examines the scenarios where a real time system requires very little redundant hardware resources to tolerate failures in heterogeneous real time distributed systems with point-to-point communication links. Fault tolerance can be achieved by scheduling additional ghost copies in addition to the primary copy of the task. The method proposed here extends the traditional distributed recovery block (DRB) based fault tolerant scheduling approach for real time tasks. Our algorithms are mostly based on software redundancy, and ensures that the parallel updation of backup task works better in case of transient overload and handles permanent, transient and timing fault. The performance of our proposed schemes has been verified using most common quality metrics, guarantee ratio and throughput. An attempt has been made to propose a scheduling scheme based upon fixed length coding using DNA algorithm. Which can be used to design an ecient Fault Tolerant algorithm for real time distributed system using DRB. The research has resulted in development of a Fault Tolerant Real Time Dynamic Scheduling Algorithm For Heterogeneous Distributed which also leads into building an Adaptive Fault Tolerant Dynamic Scheduling Algorithm. The development in the thesis is genuinely supported by detailed literature survey and mathematics preliminaries leading to the proposed model of fault tolerant algorithm. For shake of continuity each chapter has its relevant introduction and theory. The work is also supported by list of necessary references. Attempt is made to make the thesis self-content.en
format.extent1337808 bytes-
format.mimetypeapplication/pdf-
language.isoen-
publisherNational Institute of Technology, Rourkelaen
titleFault Tolerant Real Time Dynamic Scheduling Algorithm For Heterogeneous Distributed Systemen
typeThesisen
Appears in Collections:Thesis (MTech by Research)

Files in This Item:

File Description SizeFormat
thesis-final-avinash.pdf1306KbAdobe PDFView/Open

Show simple item record

All items in DSpace are protected by copyright, with all rights reserved.

 

Powered by DSpace Feedback