公开(公告)号：US08392572B2

公开(公告)日：2013-03-05

申请号：US12838727

申请日：2010-07-19

Applicant: Liang-I Chang

Inventor： Liang-I Chang

IPC: G06F15/173

CPC classification number: G06F9/5072 ,  G06F9/505

Abstract: Provided is a method for scheduling cloud-computing resource, and a system applying the method is herein disclosed. It is featured that the load history record becomes a basis to obtain a computing pattern for each computing node based on a request. The load history is the basis to predict the future computing capability, and accordingly to distribute the computing task. The cloud-computing capability can therefore be advanced. The method firstly receives a computing request. The request includes a number of computing nodes, a start time of computing, and a length of computing time. A computing resource table is established based on the load history for each node, and used to calculate availability and confidence. After that, a resource expectation value is obtained from the availability and confidence. After sorting the expectation values, one or more computing nodes are selected for further task distribution.

Abstract translation: 提供了一种用于调度云计算资源的方法，并且在此公开了应用该方法的系统。 其特征在于，负载历史记录成为基于请求获得每个计算节点的计算模式的基础。 负载历史是预测未来计算能力的基础，并因此分配计算任务。 因此，云计算能力可以提升。 该方法首先接收计算请求。 该请求包括多个计算节点，计算的开始时间和计算时间的长度。 基于每个节点的负载历史建立计算资源表，并用于计算可用性和置信度。 之后，从可用性和置信度中获得资源期望值。 在排序期望值之后，选择一个或多个计算节点用于进一步的任务分配。