The Community for Technology Leaders
Green Image
Issue No. 02 - February (1994 vol. 5)
ISSN: 1045-9219
pp: 113-120
<p>The problem of multiprocessor scheduling can be stated as finding a schedule for ageneral task graph to be executed on a multiprocessor system so that the schedulelength can be minimized. This scheduling problem is known to be NP-hard, and methodsbased on heuristic search have been proposed to obtain optimal and suboptimal solutions.Genetic algorithms have recently received much attention as a class of robust stochasticsearch algorithms for various optimization problems. In this paper, an efficient methodbased on genetic algorithms is developed to solve the multiprocessor scheduling problem.The representation of the search node is based on the order of the tasks being executedin each individual processor. The genetic operator proposed is based on the precedencerelations between the tasks in the task graph. Simulation results comparing the proposedgenetic algorithm, the list scheduling algorithm, and the optimal schedule using randomtask graphs, and a robot inverse dynamics computational task graph are presented.</p>
Index Termsgenetic algorithms; optimisation; computational complexity; multiprocessing systems;scheduling; performance evaluation; genetic algorithm; multiprocessor scheduling;NP-hard; heuristic search; robust stochastic search algorithms; optimization; simulation;list scheduling; random task graphs; robot inverse dynamics computational task graph
H. Ren, E.S.H. Hou, N. Ansari, "A Genetic Algorithm for Multiprocessor Scheduling", IEEE Transactions on Parallel & Distributed Systems, vol. 5, no. , pp. 113-120, February 1994, doi:10.1109/71.265940
96 ms
(Ver 3.3 (11022016))