基于混合蚁群遗传算法的Hadoop集群作业调度

Hadoop Clusters of Job Scheduling Based on Mixed Ant Algorithm Genetic Algorithm

提出了一种基于蚁群与遗传算法融合的自适应作业调度机制,将遗传算法全局收敛、快速搜索的优点与蚁群算法正反馈、高求精率的优势相结合,以变异策略来加快局部寻优,提高收敛速度.实验结果表明本文算法可快速找到最适合当前作业的节点,有效提高Hadoop集群作业调度的效率.

In our report,a kind of self-adaptive job scheduling mechanism based on ant algorithm and genetic algorithm was proposed,which integrated the advantages of genetic algorithm,the global convergence and fast search,with the characteristics of ant algorithm,the positive feedback and efficient refinement,and the mutation strategy was performed to accelerate the speed of local optimization and convergence. The results indicated that the algorithm can obtain the most suitable nodes for current jobs and effectively improve the efficiency of job scheduling on Hadoop clusters.