Abstract: Service resources allocation and scheduling is one of the challenging and complex problems in computation-economy-driven open grid service architecture. This paper proposes a time-cost tradeoff workflow scheduling algorithm in which cost is optimized for schedules with the expectation to minimize workflow duration. Dynamic service selection strategy is adopted to adapt to dynamic shared and autonomous resources in grids. Simulation results show that the algorithm can achieve less completion time and lower cost which can meet requirements in practical applications.

Key words: Grid computing, Computational economy model, Workflow, Grid services selection

摘要： 开放网格服务架构（OGSA）和计算经济模型的提出，使得动态的、不同QoS的服务支持下的资源调度成为一个复杂且具有挑战性的问题。该文提出了网格环境下基于费用-时间的工作流调度算法，该算法采用动态资源选择策略适应网格计算环境下的动态性和自治性。在追求较小的工作流完成时间的同时，对费用进行了优化。模拟结果显示该调度算法符合计算网格的复杂环境，能够更好地满足不同用户的实际需要。

关键词: 网格计算, 计算经济模型, 工作流, 网格服务选择

CLC Number: 

• TP 391