Multi-objective workflow scheduling based on genetic algorithm in cloud environment

In recent years, cloud computing plays a crucial role in many real applications. Thus, how to solve workflow scheduling problems, i.e., allocating and different resources, under the environment becomes more important. Although some evolutionary algorithms (EAs) can problems with small scale, they show disadvantages on larger scale this paper, multi-objective genetic algorithm (MOGA) is applied optimize problems. To enhance search efficiency, study proposes an initialization sequence scheme, which each task’s data size considered when initializing its virtual machine (VM) instance. Relying initial sequence, proper trade-off between makespan energy consumption, are two optimization objectives study, be achieved. early evolution stage, traditional crossover mutate operators performed keep population’s exploration. On contrary, longest common subsequence (LCS) of multiple elite individuals, regarded as favorable gene block, saved during later stage. Based LCS, probability blocks being destroyed will reduced performing operator operator. Hence, integration LCS GA satisfy requirements stages, then attain balance exploration exploitation. Extensive experimental results verify that proposed combined named GALCS find better Pareto front than ordinary well other state-of-the-art algorithms. Furthermore, effectivenesses new strategies also verified by set experiments.