Genetic list scheduling for soft real-time parallel applications

Abstract

This paper presents a hybrid algorithm that combines list scheduling with a genetic algorithm for constructing nonpreemptive schedules for soft real-time parallel applications represented as directed acyclic graphs. The execution time requirements of the applications' tasks are assumed to be stochastic and are represented as probability distribution… (More)
DOI: 10.1109/CEC.2004.1330993

Topics

4 Figures and Tables

Cite this paper

@article{Dandass2004GeneticLS, title={Genetic list scheduling for soft real-time parallel applications}, author={Yoginder S. Dandass}, journal={Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)}, year={2004}, volume={1}, pages={1164-1171 Vol.1} }