云计算下基于启发式混合算法的工作流调度研究

Researsch on Workflow Scheduling in Cloud Computing Based on Heuristic Hybrid Algorithm

针对当前云环境中资源利用率不高,节点负载不均衡的问题,提出了一种基于遗传算法的启发式混合算法用于工作流调度.该算法首先基于图的拓扑结构将任务按优先级排序,然后融合Best-Fit方法创建最优初始种群,最终结合交叉和变异操作来获得最佳解决方案.通过在CloudSim环境下的仿真分析和比较,该算法在任务完成时间、负载均衡率以及加速比方面都优于其他算法.

In view of the problem that resources utilization rate is not high and node load are imbalance in current cloud computing environment,this paper presents a heuristic hybrid method based on genetic algorithm for workflow scheduling.At first,the tasks are sorted by priority in this algorithm.Then,it merges Best-Fit method to make an optimal initial population,and apply crossover and mutation operations to achieve the best solution finally.This algorithm in the task completion time and load balancing rate and speedup is better than other algorithms.