摘要
网格工作流调度关注大规模的资源和任务调度,是一个复杂且具有挑战性的问题,它影响着网格工作流执行成功与否以及效率的高低。提出了基于遗传粒子群(GAPSO)的混合算法,引用了特殊的适应度函数,设定了动态的交叉和变异概率,并提出了动态切换算法的方法。结合各自算法的优势,在算法运行初期利用遗传算法的全局搜索能力进行优化搜索,在后期利用粒子群较强的局部搜索能力加快收敛速度。仿真结果表明该算法在执行时间方面有一定的优越性,能更有效地解决网格工作流调度问题。
Grid workflow scheduling concerns about the scheduling of large-scale resources and tasks,and it is one of the most complex and challenging issues which affects the execution and efficiency of grid workflow.This paper proposes a hybrid algorithm based on genetic and particle swarm optimisation（GAPSO）,within the hybrid algorithm a special fitness function is quoted,crossover and mutation probability are set dynamically,and the method of dynamically switching between algorithms is proposed.By combining the advantages of the two algorithms,the hybrid algorithm uses the global search ability of genetic algorithms to optimise the search at the beginning,and uses the stronger local search ability of particle swarm algorithm to speed up the convergence rate in the latter part.Simulation experiment results show that the algorithm has some advantages in the execution time and can address grid workflow scheduling problem more effectively.
出处
《计算机应用与软件》
CSCD
2011年第4期236-238,241,共4页
Computer Applications and Software
关键词
遗传算法
粒子群算法
网格工作流
Genetic algorithm Particle swarm optimisation Grid workflow
