Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Physical Sciences and Mathematics
A Comparison Of Load Balancing Algorithms For Parallel Computations, N. Mansouri, Geoffrey C. Fox
A Comparison Of Load Balancing Algorithms For Parallel Computations, N. Mansouri, Geoffrey C. Fox
Electrical Engineering and Computer Science - Technical Reports
Three physical optimization methods are considered in this paper for load balancing parallel computations. These are simulated annealing, genetic algorithms, and neural networks. Some design choices and the inclusion of additional steps lead to new versions of the algorithms with different solution qualities and execution times. The performances of these versions are critically evaluated and compared for test cases with different topologies and sizes. Orthogonal recursive coordinate bisection is also included in the comparison as a typical simple deterministic method. Simulation results show that the algorithms have diverse properties. Hence, different algorithms can be applied to different problems and requirements. …
Parallel Genetic Algorithms With Application To Load Balancing For Parallel Computing, N. Mansouri, Geoffrey C. Fox
Parallel Genetic Algorithms With Application To Load Balancing For Parallel Computing, N. Mansouri, Geoffrey C. Fox
Electrical Engineering and Computer Science - Technical Reports
A new coarse grain parallel genetic algorithm (PGA) and a new implementation of a data-parallel GA are presented in this paper. They are based on models of natural evolution in which the population is formed of discontinuous or continuous subpopulations. In addition to simulating natural evolution, the intrinsic parallelism in the two PGA's minimizes the possibility of premature convergence that the implementation of classic GA's often encounters. Intrinsic parallelism also allows the evolution of fit genotypes in a smaller number of generations in the PGA's than in sequential GA's, leading to superlinear speed-ups. The PGA's have been implemented on a …