Scheduling strategy for science workflow with deadline constraint on multi-cloud

In view of the deadline-constrained scientific workflow scheduling on multi-cloud,an adaptive discrete particle swarm optimization with genetic algorithm (ADPSOGA) was proposed,which aimed to minimize the execution cost of workflow while meeting its deadline constrains.Firstly,the data transfer cost,the shutdown and boot time of virtual machines,and the bandwidth fluctuations among different cloud providers were considered by this method.Secondly,in order to avoid the premature convergence of traditional particle swarm optimization (PSO),the randomly two-point crossover operator and randomly one-point mutation operator of the genetic algorithm (GA) was introduced.It could effectively improve the diversity of the population in the process of evolution.Finally,a cost-driven strategy for the deadline-constrained workflow was designed.It both considered the data transfer cost and the computing cost.Experimental results show that the ADPSOGA has better performance in terms of deadline and cost reducing in the fluctuant environment.