Scheduling Multiprocessor Tasks with Genetic Algorithms
IEEE Transactions on Parallel and Distributed Systems
Multiprocessor Clustering for Embedded Systems
Euro-Par '01 Proceedings of the 7th International Euro-Par Conference Manchester on Parallel Processing
A bipartite genetic algorithm for multi-processor task scheduling
International Journal of Parallel Programming
Hi-index | 0.00 |
This paper presents a genetic algorithm using a matrix genome encoding to schedule distributed tasks, represented by a directed acyclic graph, on processors in order to minimize the maximum task finishing time. Our experimental results show that this algorithm provides better scheduling results than list scheduling with insertion; and dominant sequence clustering heuristics. Our algorithm generates good schedules even in those cases when the heuristically-generated schedules are worse than using a single processor.