Multiprocessor scheduling using mean-field annealing

This paper presents our work on the static task scheduling model using the mean-field annealing (MFA) technique. Mean-field annealing is a technique o f thermostatic annealing that takes the statistical properties of particles as its learning paradigm. It combines good features from the Hopfield neur al network and simulated annealing, to overcome their weaknesses and improv e on their performances. Our MFA model for task scheduling is derived from its prototype, namely, the graph partitioning problem. MFA is deterministic in nature and this has the advantage of faster convergence to the equilibr ium temperature, compared to simulated annealing. Our experimental work Ver ifies this finding, besides making comparison on the effectiveness of the m odel on various network and task graph sizes. Our work also includes the si mulation of the MFA model on several network topologies using varying param eters. The MFA simulation model is targeted on nonpreemptive and precedence -related tasks with communication costs. (C) 1998 Elsevier Science B.V. All rights reserved.