通信工程文献翻译——摘要：为了解决网格环境预算和最后期限资源限制协同分配的问题，提出一种新型的协同分配模型根据虚拟资源代理的基础。该模型通过三方合作的分配机制优化资源配置和价格方案，并且应用排队系统对网格资源的工作模型用于提供网格应用的数量期限的保证。在解决办法和有效性上提出理论上的模型。对模型的有效性和性能，与违反限期率共同分担政策的比较进行了大量的模拟研究，提高资源效益和资源利用率。实验结果表明，三种典型协同分配政策相比，对于网格应用预算和期限的限制该模型可以减少违反限期率约3.5％。此外，该系统效益可以增加约30％比广泛使用的协同分配政策。

关键字：协同分配；计算网格；网格经济；排队论；期限

1  引言

网格计算已经成为一个有前途的网络计算平台是解决聚集和分布高端应用程序的资源，这往往需要通过访问多个资源虚拟组织[1]。因此，资源协同分配始终是网格计算一个关键问题，以及各种协同分配框架已经在各个网格系统中发展[2-4]。这些框架在网格应用方面主要集中在共同配送服务体系结构和编程接口，它们都没有解决预算和期限限制的资源协同分配问题。

作为协同分配框架的补充，提出许多共同的分配政策和模型。LEINBERGER et al[5]提出K资源协同分配回填启发式模型。平均响应时间他们研究表明负载平衡政策优于经典政策大约50%。MOHAMED和EPEMA[6]提出了一种近乎文件的政策，它试图放置工作对输入的收盘集群文件，以减少通信开销。HE et al[7]提出两个地址协同分配政策（ORT and OMT）。ORT目标是优化平均响应时间在非实时工作中，为了评估不同的合作分配政策的其他标准对于软实时工作流OMR设计实现优化平均截止期错失率，BUCUR and EPEMA[8-9]做了大量实验在大型并网系统。根据他们在网格试验床实验结果，对减少和增加平均响应时间他们得出一个重要的结论工作量感知是有效更好负载平衡。但是以上大多数政策目的是提高系统性能指标，只有很少的考虑到用户QoS。

为了预算和期限限制协同分配资源应用，网格经济[10]已被引入网格系统。例如：Spawn[12]，Popcon[13]，and Nimrod-G[14]。例如，Nimrod-G提供三种适应性政策对期限和预算限制资源分配[15]，成本优化，时间优化，和保守的时间优化。尽管经济模型在分布式环境里已经被证明是资源协同分配有效的方法，他有两个缺点不能被忽视：（1）经济模型会给通信和计算应用带来额外开销[11]；（2）在高端应用存在需要合作站点之间分配......

Abstract: To address the issue of resource co-allocation with constraints to budget and deadline in grid environments, a novel co-allocation model based on virtual resource agent was proposed. The model optimized resources deployment and price scheme through a three-side co-allocation mechanism, and applied queuing system to model the work of grid resources for providing quantitative deadline guarantees for grid applications. The validity and solutions of the model were presented theoretically. Extensive simulations were conducted to examine the effectiveness and the erformance of the model by comparing with other co-allocation policies in terms of deadline violation rate, resource benefit and resource utilization. Experimental results show that compared with the three typical co-allocation policies, the proposed model can reduce the deadline violation rate to about 3.5% for the grid applications with constraints to budget and deadline. Also, the system benefits can be increased by about 30% compared with the those widely-used co-allocation policies. 

Key words: co-allocation; computational grid; grid economy; queuing theory; deadline

1 Introduction 

Grid computing has emerged as a promising network computing platform that aggregates heterogeneous and distributed resources for solving high-end applications, which frequently require access to multiple resources across virtual organizations [1]. 

Therefore, resource co-allocation is always the key issue in grid computing, and various co-allocation frameworks have been developed in various grid systems [24]. These frameworks mainly focus on co-allocation service architecture and programming interfaces for grid applications. None of them has addressed the issue of resource co-allocation with the constraints to budget and deadline. 

As complementary to co-allocation frameworks, many co-allocation policies and models were proposed.......