一种面向云多层应用的费用高效的资源管理方法

发布时间：2018-05-27 11:35

本文选题：云计算 + 费用高效　；参考：《计算机科学》2017年03期

【摘要】：由于部署方便、维护简单并且不需要搭建自己的私有机房,云数据中心正成为大多数互联网公司尤其是初创公司和中小规模公司部署应用程序的首选。在以基础设施为服务的云环境里,互联网公司可以根据应用程序的需要动态租赁云基础设施,从而节省预算开支,并保证应用性能。然而,在现有的业界实践中,云服务提供商提供的负载均衡和资源伸缩服务只能监控虚拟机的使用状态,并不能监控应用程序的运行状态,因此无法准确根据应用程序的服务需求自适应变换资源规模。同时,现有的文献和实践中,也很少有研究从云基础设施使用者的角度出发,为使用者节省基础设施租赁费用或高效使用已租赁基础设施。据此提出了一种面向基础设施云环境下多层应用的费用高效的资源管理方法,其在降低用户费用的同时,还能充分利用所花费用提高应用程序性能。通过仿真对所提方法业界实际使用的方法进行比较,结果表明所提方法不仅能够提高应用程序的服务质量和服务性能,也能较大地降低公司在基础设施租赁方面的费用。
[Abstract]:Because of its easy deployment, simple maintenance and no need to build its own private machine room, the cloud data center is becoming the first choice for most Internet Co, especially start-ups and small and medium sized companies to deploy applications. In a infrastructure - based cloud environment, Internet Co can dynamically lease the cloud according to the needs of the application. Infrastructure, thus saving budgetary costs, and ensuring application performance. However, in existing industry practices, the load balancing and resource scalability services provided by cloud service providers can only monitor the use of the virtual machine and can not monitor the running state of the application, so it can not be adaptively changed according to the service requirements of the application. At the same time, there are few studies in the existing literature and practice to save the user's infrastructure rental costs or the efficient use of the rental infrastructure from the perspective of the cloud infrastructure users. A cost-effective resource management method for multi-layer applications in the infrastructure cloud environment is proposed. While reducing the cost of the user, it can also make full use of the cost to improve the performance of the application. By comparing the actual methods used by the proposed method industry through simulation, the results show that the proposed method can not only improve the service quality and service performance of the application, but also greatly reduce the cost of the company's infrastructure leasing.
【作者单位】：解放军信息工程大学;数学工程与先进计算国家重点实验室;解放军61345部队;
【基金】：上海市科委科技攻关项目(13DZ1108800) 国家自然科学基金(61472447)资助
【分类号】：TP308;TP393.09

【相似文献】