基于SaaS的弹性云平台优化调度策略设计

Elastic cloud platform optimal scheduling strategy design based on SaaS

云计算平台利用虚拟化技术使软件应用变得更有效率的同时,也给资源管理和服务调度带来了挑战。在研究了软件服务(SaaS)与基础设施服务(IaaS)调度的区别基础上,重点考虑SaaS层的资源调度,提出基于随机理论的调度模型,把该层调度描述成一种多目标的优化问题。除了服务质量的要求,还考虑了弹性这一云服务的重要特性,并提供了任务调度与弹性服务副本的匹配策略。实验表明本调度机制的设计优化了云平台的整体性能,达到了较好的负载均衡与资源利用率。

The use of virtualization technology makes software applications more effective which deployed over cloud compu- ting platforms, but also brings challenges to the resource management and service scheduling over cloud. This paper focused on novel mechanisms which provide optimal deployment and scheduling of cloud services in SaaS scenarios on the foundation of studying some differences between IaaS and SaaS scheduling, and proposed a stochastic model to describe the scheduling process as a multi-objective optimization problem. Besides some QoS （quality of service） issues, the most significant property of cloud services-elasticity has been considered in this model, and not only the scheduling of SaaS tasks but also the arrange- ment of elastic service replicas are provided by our mechanisms. Experiment results show that the deployment and scheduling mechanisms optimize the overall performance, load halance condition as well as the resource usage of the cloud computing plat- form.