Scheduling of tasks in multiprocessor system using hybrid genetic algorithms

Description

This paper presents an investigation into the optimal scheduling of realtime
tasks of a multiprocessor system using hybrid genetic algorithms (GAs). A comparative
study of heuristic approaches such as `Earliest Deadline First (EDF)¿ and
`Shortest Computation Time First (SCTF)¿ and genetic algorithm is explored and
demonstrated. The results of the simulation study using MATLAB is presented and
discussed. Finally, conclusions are drawn from the results obtained that genetic algorithm
can be used for scheduling of real-time tasks to meet deadlines, in turn to obtain
high processor utilization.

Links & Downloads

1. Varghes, B., Hossain, M. A. and Dahal, K. P. (2007) Scheduling of tasks in multiprocessor system using hybrid genetic algorithms. In: Kacprzyk, J.(ed.) Advances in soft computing: Updating the state of the art. (12th Online World Conference on Soft Computing in Industrial Applications. (WSC12) October 16th- 26th, 2007). Berlin: Springer. pp. 65-74.
2. http://hdl.handle.net/10454/2552

Tags

Optimal scheduling

Hard real-time tasks

Multiprocessor system

Heuristics

Genetic algorithms

Additional Fields

Identifer	oai:union.ndltd.org:BRADFORD/oai:bradscholars.brad.ac.uk:10454/2552
Date	January 2007
Creators	Varghese, B., Hossain, M. Alamgir, Dahal, Keshav P.
Publisher	Springer Verlag
Source Sets	Bradford Scholars
Language	English
Detected Language	English
Type	Conference paper, Accepted Manuscript
Rights	© 2007 Springer Verlag. Reproduced in accordance with the publisher's self-archiving policy. Original publication is available at http://www.springerlink.com
Relation	http://www.springerlink.com