基于遗传-蚁群算法的云计算任务调度优化

Task Scheduling and Optimization of Cloud Computing Based on Genetic Algorithm and Ant Colony Algorithm

为了找到最佳的云计算任务调度方案,缩短云计算任务完成时间,通过综合考虑遗传算法和蚁群算法的优势,提出一种遗传-蚁群算法的云计算任务调度优化算法.首先采用遗传算法快速搜索到云计算任务调度的可行方案,然后采用可行方案初始化蚁群算法的信息素分布,解决初始信息素匮乏的难题,加快算法收敛速度和搜索能力,提高云计算任务求解效率.在CloudSim平台的实验结果表明,相对于遗传算法,遗传-蚁群算法更适合于大规模云计算任务问题的求解,可缩短任务完成时间,获得更高的用户满意度.

In order to find the best cloud computing task scheduling scheme and shorten task completion time of cloud computation,by a comprehensive consideration of advantages of genetic algorithm and ant colony algorithm,we proposed a new cloud computing task scheduling and optimization algorithm based on genetic algorithm and ant colony algorithm.Firstly,genetic algorithm was used to search feasible scheme of cloud computing task scheduling.Secondly,feasible scheme was used to initialize pheromone distribution of ant colony algorithm,to solve problem of lack initial pheromone,to speed up convergence speed and search ability,and to improve the efficiency of cloud computing tasks.Finally the experimental results on CloudSim platform show that compared with genetic algorithm.The proposed algorithm is more suitable for solving the problem of large-scale cloud computing tasks,which shortens task scheduling time,and user satisfaction is higher.