云环境中基于异构资源的资源分配算法

A Resource Allocation Algorithm Based on Heterogeneous Resources in Cloud Environment

随着"云计算"的出现和快速发展,"云"作为一种新型的资源形式被越来越多的用户所使用。云环境中的资源分配问题成为了云计算中不可忽略的问题。在云资源管理平台中,如何既满足用户的任务需求,又节省云资源成本,是云运营商尽快希望解决的问题之一。实际上云用户对云资源的请求是有差异的,而且用户任务的完成通常由多个异构的云资源来实现。文中作者考虑了异构云资源间的差异,提出了一种基于异构资源的资源分配算法。该算法先从任务的全局角度考虑,将用户提交的云任务划成不同的组合,再根据云资源间的差异,为相应的组合分配相应的资源。实验仿真表明,在异构云环境中,该算法能在满足用户需求的前提下,在节省云资源使用上有较好的表现。

With the emergence and vigorous development of“cloud computing”, the “cloud” is being used as a new resource by more and more users. The resource allocation problem in cloud environment has become a negligible problem. In the resource management platform in the cloud, the question how to not only meet the needs of the user＇s task, but also save the cost of cloud resources, is one of the issues for cloud operators to solve as soon as possible. In fact, the tasks submitted to the cloud platform by cloud users have difference, and the completion of the tasks is usually realized with multiple heterogeneous cloud resources. In this paper the authors take the difference among heterogeneous resources into account, and propose the RA-HR algorithm. The algorithm divides cloud tasks submitted by users into different combinations considering from the global view of the tasks, and then according to the difference among the cloud resources, allocates appropriate resources to the appropriate combinations. The simulation results show that the algorithm can offer better performance in saving cloud resource under the premise of meeting user＇s needs in heterogeneous cloud environment.