摘要
论文将集中式资源发现机制和分布式资源发现机制结合起来,提出了基于资源类型查找的分层资源发现模型。该模型由物理资源层和虚拟组织层组成,虚拟组织层中,将网格资源按照不同类型划分成若干个虚拟组织,并为每个虚拟组织设置一个管理节点,用来存储和管理物理资源层中同类资源的索引信息。该模型克服了集中式中使用一个中心节点容易产生瓶颈的缺点,同时也克服了分布式中资源信息空间的无序性、无结构性和资源发现的盲目性,提高了资源发现的有效性和准确性。并使用OPNET模拟仿真工具对提出的资源定位策略进行了模拟仿真,以验证所提策略的可行性和有效性。
In this paper, a layered and classified resource discovery model in grid environment is designed by integrating central and distributed resource discovery scheme. This model is composed of two layers-physical resource layer and virtual organization layer. In the virtual organization layer, grid resources are divided into certain virtual organizations according to their different kinds, a manager node is set in every virtual organization to store and manage index information of all homoge- neous resources in the physical resource layer. Therefore, on one hand, the problem of bottleneck in central scheme is avoi- ded. On the other hand, the disadvantage in distributed scheme, the randomization and unstructured features of resources in information space is avoided. And this makes the resource discovery more effective and accurate. Simulation is carried out to verify the feasibility and availability of the resource location strategy on OPNET platform.
出处
《计算机与数字工程》
2015年第5期871-876,共6页
Computer & Digital Engineering