摘要
云计算已成为当前最为重要的计算模式并在不断地演化,而调度在云计算系统中起着关键作用,需要考虑资源需求的多维性、计算资源的多样性以及共享集群的多个用户之间的公平性。在分析云计算资源调度基本框架的基础上,分别从资源调度框架和调度算法两方面对云计算资源调度关键技术进行综述,并从群体智能调度算法和非群体智能调度算法两类方法对其进行详细阐述,最后指出未来智能资源调度器的发展方向。
Cloud computing has become one of the most important computing paradigms and is constantly evolving.Scheduling plays a vital role in cloud computing system.It not only needs to consider the multidimensional demand of resources,the diversity of computing resources and the fairness among multiple tenants sharing the cluster.First,the basic framework of cloud computing resource scheduling is analyzed,and then the key technologies of cloud computing resource scheduling is summarized from two aspects:resource scheduling frameworks and scheduling algorithms.The scheduling algorithms are divided into swarm intelligent scheduling algorithms and non-swarm intelligent scheduling algorithms.Finally,the development direction of the next generation of intelligent resource scheduler is pointed out.
作者
王占丰
张林杰
吕博
季宇凯
胡超
温胜昔
WANG Zhanfeng;ZHANG Linjie;LYU Bo;JI Yukai;HU Chao;WEN Shengxi(School of Computer Science and Engineering,Southeast University,Nanjing 211189,China;The 54th Research Institute of CETC,Shijiazhuang 050081,China;The 30th Research Institute of CETC,Chengdu 610093,China;School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China;College of Comannd Control Engineering,Army Egineering University of PLA,Nanjing 210007,China;Nanjing Lexbell Information Technology Co.,Ltd,Nanjing 210000,China)
出处
《无线电通信技术》
2022年第2期213-222,共10页
Radio Communications Technology
基金
国家重点研发计划(2018YFB1800200,2017YFB081703)
东南大学博士后创新人才培养资助基金项目(242019R20024)。
关键词
云计算
调度
机器学习
群体智能
cloud computing
schedule
machine learning
swarm intelligence
