云计算下负载均衡的多维QoS约束任务调度机制  

Multi-dimensional QoS constrained scheduling mechanism based on load balancing for cloud computing

作　　者：祝家钰[1] 肖丹[1] 王飞[1] 

机构地区：[1]重庆邮电大学计算机科学与技术学院,重庆400065

出　　处：《计算机工程与应用》2013年第9期85-89,共5页Computer Engineering and Applications

基　　金：重庆邮电大学自然科学基金(No.A2011-25)

摘　　要：高效的任务调度机制能够更好地满足用户的QoS需求,实现各物理主机间的负载均衡,从而提高云计算环境的整体性能。而传统的任务调度往往只考虑任务的响应时间或安全性等,且负载均衡策略是静态的。根据云计算的弹性化和虚拟化等新特性,综合考虑任务的性能QoS和信任QoS,提出一种在云计算环境下的任务调度机制,采用虚拟机迁移技术实现动态负载均衡。通过在CloudSim2.1仿真环境下的分析和比较,该任务调度机制不但可以提高用户满意度,而且可以有效实现负载均衡。In cloud, the needs of the user＇ s QoS can be better met and the load balancing between physical hosts can be achieved depending on an efficient scheduling mechanism. The traditional scheduling mechanisms often concern only about the response time of tasks or security, and load balancing strategy is static. The overall performance of the cloud computing environment needs to be improved. Based on the flexibility, virtualization and other new features of cloud computing, this paper proposes a task scheduling mechanism considering performance QoS and trust QoS of tasks. It uses virtual machine migration technology to achieve dynamic load balancing. Simulation by CloudSim2.1 shows the scheduling mechanism will not only improve satisfaction of customers but also achieve load balancing effectively.

关 键 词：云计算 任务调度 服务质量(QoS) 负载均衡 虚拟化 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]