摘要
针对云资源调度中任务分配效率和资源利用率低等情况,提出一种改进的人工蜂群算法。在基本人工蜂群算法基础上,将交叉机制与全局最优引导的人工蜂群算法相结合,增强人工蜂群算法中蜂群对蜜源的开发能力,同时保持探索能力。在观察蜂选择策略中,引入灵敏度的概念。灵敏度通过配合蜜源信息素而让观察蜂选择蜜源,增加种群的多样性,避免算法陷入局部最优。实验结果表明:改进的人工蜂群算法更快收敛,当任务数为200个时,改进的人工蜂群算法的任务完成时间比人工蜂群算法和蚁群算法分别减少了24 s和35 s。
Aiming at the problem of low task allocation efficiency and low resource utilization in cloud resource scheduling,an improved artificial bee colony algorithm was proposed.On the basis of basic artificial bee colony algorithm,the crossover mechanism was combined with the global optimally guided artificial bee colony algorithm to enhance development ability of bee colony to nectar sources in artificial bee colony algorithm while maintaining exploration ability.In the observation bee selection strategy,a concept of sensitivity was proposed,the sensitivity cooperated with nectar source pheromone to make observation bees to choose nectar source,so as to increase diversity of the population and prevent the algorithm from falling into local optimum.The experimental results indicate that the improved artificial bee colony algorithm converges faster.When the number of tasks is 200,task completion time of the improved artificial bee colony algorithm is 24 s and 35 s less than that of the artificial bee colony algorithm and the ant colony optimization,respectively.
作者
任金霞
杜增正
王兴康
REN Jinxia;DU Zengzheng;WANG Xingkang(School of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou 341000,China)
出处
《河南科技大学学报(自然科学版)》
CAS
北大核心
2022年第4期55-60,M0005,M0006,共8页
Journal of Henan University of Science And Technology:Natural Science
基金
国家自然科学基金项目(71361014)
江西省教育厅科技项目(GJJ150679)。
关键词
云计算
任务调度
人工蜂群算法
任务完成时间
cloud computing
task scheduling
artificial bee colony algorithm
task completion time