Problem Independent Distributed Simulated Annealing and its Applications

Simulated annealing has proven to be a good technique for solving hard combinatorial optimization problems. Some attempts at speeding up annealing algorithms have been based on shared memory multiprocessor systems. Also parallelizations for certain problems on distributed memory multiprocessor systems are known. In this paper, we present a problem independent general purpose parallel implementation of simulated annealing on large distributed memory message-passing multiprocessor systems. The sequential algorithm is studied and we give a classi cation of combinatorial optimization problems together with their neighborhood structures. Several parallelization approaches are examined considering their suitability for problems of the various classes. For typical representatives of the di erent classes good parallel simulated annealing implementations are presented. We describe in detail several 'tricks' increasing e ciency and attained solution quality of the di erent parallel implementations. Extensive measurements of e ciency, solution quality and other parameters of the algorithms are presented on di erent numbers of processors. These measurements show, that our algorithms scale up to more that 120 processors. Some applications are described in detail, showing the practical relevance of our work. All algorithms are implemented in OCCAM-2 on a free con gurable transputer system.