A Fast Hybrid Genetic Algorithm in Heterogeneous Computing Environment

A hybrid genetic algorithm (HGA) is proposed for heterogeneous computing environment scheduling in this paper. Individual and population adaptability are introduced for making the crossover and mutation probability adjusted adaptively, making the number of crossover and mutation adjust adaptively with the proportion of average and maximum fitness. It can avoid such the disadvantages as premature convergence, low convergence speed. Also, a new acceptance criterion based on the simulated annealing heuristics is proposed for improving the local convergence. Compared with the traditional local search, the new criterion introduced random factors through Metropolis criterion, bad solutions can be accepted. An experimental result demonstrates that the proposed genetic algorithm does not get stuck at a local optimization easily, and it is fast in convergence.