摘要
为解决云环境下的资源调度问题,提出一种通过任务执行成本函数来提高虚拟机负载均衡度的改进蚁群算法(CLBACO).该算法在综合参考各种最新蚁群算法的基础上,创新地通过任务的执行成本函数来改进信息素中的启发信息和期望信息,重新定义信息素更新规则,进而影响到任务对虚拟机的选择,同时使虚拟机通过多次算法迭代以后能够处于一种负载均衡的状态.利用CloudSim工具进行仿真测试,与标准的蚁群算法、最新的DSFACO算法做仿真对比,结果表明CLBACO算法在任务的执行成本以及系统负载均衡方面均优于DSFACO算法.
To solve the problem of resource scheduling in cloud computing,the Cost and Load Balanced Ant Colony Optimization（CLBACO） is proposed,and it is aimed at promoting load balance of virtual machine with the cost function of task execution.The CLBACO improves the inspiring and expecting information of pheromone creatively by executing task cost function based on a comprehensive reference of the latest ant colony algorithms.It also redefines the updating rules for pheromone,thus experts impacts on the choice of virtual machines for tasks and simultaneously keeps the load balance of virtual machines by executing tasks for many tims.Some experiments are done on the CloudSim platform,and the results are compared with algorithm of the latest DSFACO.The results of the comparison show that the CLBACO algorithm is more efficient than the other algorithms in reducing the cost of task execution and keeping load balance.
出处
《新疆大学学报（自然科学版）》
CAS
北大核心
2016年第4期454-458,共5页
Journal of Xinjiang University(Natural Science Edition)
基金
重庆市高等教育学会2015-2016年度教育科学研究课题(CQGJ15203B)
关键词
云计算
执行成本
蚁群算法
任务调度
负载均衡
cloud computing
task execution cost
colony algorithm
task allocation
load balancing
