NSF Workshop on Scientific Workflows Challenges (WSW-06)

工作流最近已经成为进行大规模科学分析的范例。工作流的结构指定了需要执行的分析例程、它们之间的数据流以及相关的执行细节。这些工作流通常需要在分布式环境中执行，其中数据源可能位于不同的物理位置，并且这些步骤的执行需求可能调用远程位置的高端计算和内存资源。工作流有助于管理相关任务的协调执行。它们还提供了一种系统的方法来获取科学方法并为其结果提供来源信息。然而，健壮和灵活的工作流创建、映射和执行在很大程度上是开放的研究问题。科学工作流对业务工作流和其他类型的流程模型提出了新的挑战。它们通常使用非常大的分布式数据集，使用计算密集型任务，并且需要高端的分布式计算技术。它们也经常是迭代和交互设计的，因为这是它们所反映的科学探索和分析过程的本质。另一方面，科学工作流在数据流结构、执行管理或安全/隐私约束方面也有简化的需求。目前，科学工作流的设计大多没有正式的原则，很少进行优化、可扩展或可重用。本次研讨会的目的是将IT研究人员和从业者以及领域科学家聚集在一起。应用科学家将被要求描述需求和期望的新分析和计算，这是当今技术无法实现的。IT研究人员将被要求找出他们专业领域的问题。讨论将集中在四个主题上：(1)应用和需求；(2)动态工作流程和用户导向；(3)数据和工作流程描述；(4)支持大规模工作流的系统级管理。讲习班的成果将是一份概述研究方向和活动的报告，这些研究方向和活动将把所需的社区聚集在一起，为科学工作流程制定一种新的范例。用于构建高效、可扩展和可重用的科学工作流的易于使用的工具可能会给许多领域带来好处，并且可以提高许多领域的研究工作的速度和质量。讲习班网站（http://vtcpc.isi.edu/wiki）提供有关讲习班的进一步信息，并将用于传播讲习班报告和其他成果。

Workflows have recently emerged as a paradigm for conducting large-scale scientific analyses. The structure of a workflow specifies what analysis routines need to be executed, the data flow amongst them, and relevant execution details. These workflows often need to be executed in distributed environments, where data sources may be available in different physical locations and the steps may have execution requirements calling for high-end computing and memory resources at remote locations. Workflows help manage the coordinated execution of related tasks. They also provide a systematic way to capture scientific methodology and provide provenance information for their results. Yet, robust and flexible workflow creation, mapping, and execution are largely open research problems.Scientific workflows present new challenges over business workflows and other kinds of process models. They typically use very large, distributed data sets, employ computationally intensive tasks, and require high-end and distributed computing technology. They are also often iteratively and interactively designed, since that is the nature of the scientific exploration and analysis process they reflect. On the other hand, scientific workflows also have simplified requirements in terms of their data flow structure, execution management, or security/privacy constraints. Currently, scientific workflows are mostly designed without formal principles and are rarely optimized, scalable or reusable.The aim of this workshop is to bring together IT researchers and practitioners as well as domain scientists. Application scientists will be asked to describe requirements and desired new analyses and computations that are not possible with today's technologies. IT researchers will be asked to identify problems in their specific areas of expertise. Discussions will focus on four main topics: (1) applications and requirements; (2) dynamic workflows and user steering; (3) data and workflow descriptions; and (4) system-level management to support large-scale workflows. The outcome of the workshop will be a report outlining research directions and activities that will bring the needed communities together to work on producing a new paradigm for scientific workflows. Easy-to-use tools for building efficient, scalable and reusable scientific workflows are likely to bring benefits to many fields, and can raise the pace and quality of research work in many areas. The workshop Web site (http://vtcpc.isi.edu/wiki) provides further information about the workshop and will be used for disseminating the workshop report and other results.