论文部分内容阅读
针对目前优化计算服务缺乏对一般用户的优化计算支持和灵活的资源共享方式,提出利用网格环境、支持网络计算资源以并行的、协同的方式提供面向服务的优化功能的计算服务系统,并设计了对系统性能具有重要影响的动态任务调度算法,从而使系统能够适应复杂过程系统优化计算以及网格环境的典型特征.相应地,系统采用多任务队列的任务管理方式和计算节点组的资源管理方式,为该调度策略提供实现基础.测试结果体现了基于该调度算法的优化计算服务系统的良好性能,并为设计在该系统下高效运行的并行算法提供了参考依据.
In view of the current lack of optimized computing support for general users and flexible resource sharing methods, this paper proposes a computing service system that uses grid environment and supports network computing resources to provide service-oriented optimization functions in a parallel and cooperative manner. The dynamic task scheduling algorithm has an important influence on the system performance, so that the system can adapt to the complex process system optimization and the typical characteristics of the grid environment.Accordingly, the system adopts the task management mode of multi-task queue and the resource management Which provides the basis for the scheduling strategy.The test results show the good performance of the optimized computing service system based on the scheduling algorithm and provide a reference for designing parallel algorithms running efficiently under the system.