多级优化的云计算任务智能调度算法

Intelligent Task Scheduling Algorithm of Cloud Computing Using Multi-level Optimization

在云计算环境中用户数量巨大,需要处理的任务繁多,高效的任务调度算法是云计算需要解决的关键问题之一。针对云计算的模型结构,引入粒子群算法和蚁群算法联合优化任务调度算法。首先使用粒子群算法生成初始调度结果,并引入随机性的惯性权重提高算法的调节能力,将改进粒子群算法生成的结果作为蚁群算法的初始信息素寻找最优调度方案,并使用遗传算法中的精英策略和交叉算子改进蚁群算法,在算法中使用多层次优化算法提高算法运行效率。实验结果表明,在相同的条件下,改进后的算法任务总完成时间得到降低,且随着任务量的增加性能优势更为明显。

The user number and tasks need to be handled are huge in the cloud computing environment, so the high-efficient task scheduling algorithm is one of the key issues to be resolved. The particle swarm optimization and ant colony algorithm are introduced into the task scheduling according to the structure of the cloud computing model. Firstly, the particle swarm algorithm is used to generate the initial scheduling results and the random inertia weight is used to improve its regulation ability. The result is used as the initial pheromone of the ant colony algorithm to search the optimal scheduling scheme, in which the elitist strategy and crossover operators from the genetic algorithm are used to improve the ant colony algorithm to enhance the efficiency. The experiment results show that the total task completion time of the improved algorithm is less than that of the prior algorithm, and the performance becomes more obvious as the task size increases.