【摘要】 时间是衡量工作流性能的重要指标。通过对工作流的资源配置的优化,可以改善工作流的时间性能。资源配置优化可以从资源专业化/一般化程度和资源数量两个方面来进行。为了优化资源的这两个方面,提出了一种基于分层嵌套遗传算法的资源优化方法。它采用工作流实例平均响应时间作为评价指标,在成本的约束下,正确配置各类资源专业化/一般化的程度及资源数量,从而最优化工作流时间性能。并通过实例,说明了该方法的可行性和有效性。更多还原

【Abstract】 Time is an important indicator of workflow performance. Time performance of a workflow can be improved by optimizing the resources configuration of the workflow. The specialization/generalization level and the number of resources are two aspects of the resources configuration. A method was proposed to optimize those aspects in order to improve the workflow time performance with cost constraint. The method is based on a nesting genetic algorithm (GA) which extends the classic GA. The average throughput time of workflow instances was used as the indicator of workflow time performance. Some examples were given to illustrate the feasibility and validity of the method.更多还原