Workshop on the Development of a Next-generation, Interoperable, Federated Networking Cyberinfrastructure

下一代、可互操作、联合网络网络基础设施开发研讨会

• 批准号: 1451194
• 负责人: Victor Hazlewood
• 金额: $ 5万
• 依托单位: University of Tennessee Knoxville
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-09-01 至 2015-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1451194&HistoricalAwards=false
• 关键词: Workshop; Development; Next; generation; Interoperable

The national and global research Cyber Infrastructure (CI) of the future is likely to exhibit a dichotomy in the physical distribution of cyber resources. At one extreme are traditional, large-scale data centers, such as the NSF supported supercomputing centers (e.g., NCSA, PSC, SDSC, NICS). The other extreme includes highly distributed federations of collaborating resources represented by tightly and loosely coupled federations for NSF projects including, but not limited to, GENI, XSEDE, FutureGrid and NSFCloud, which include university campus IT and campus research networks. In this second model, small collections of resources are owned and operated by a large number of participating sites. The most important contribution of the CI platform is not the sheer bulk of resources at any one facility, but rather the wide reach of the overall federation. These diffuse federations have a number of desirable characteristics: they benefit from natural geographies of researchers and data, and they require relatively modest resource contributions from each site, thus encouraging broad participation.Building and maintaining highly diffuse federations of cyberinfrastructure involves distinct technical challenges that need to be discussed, analyzed and overcome. This proposal funds a workshop that will bring together participants from the GENI, NSFCloud, FutureGrid and XSEDE communities to discuss, compare/contrast and understand the various communities' needs and approaches to control frameworks for CI. The workshop will be held in the Washington, DC area on October 14th and 15th, 2014. To help identify opportunities for collaboration, participants will be specifically encouraged to make statements of the form "My project needs" or "My project can offer" regarding the following topics: 1. Tools for cyberinfrastructure-supported researchers; 2. Tools for cyberinfrastructure owners / providers; 3. Data structures and protocols for control of resources; and 4. Data structures and protocols for control of federations.

未来的国家和全球研究网络基础设施（CI）很可能在网络资源的物理分布方面表现出二分法。一个极端是传统的大型数据中心，例如NSF支持的超级计算中心（例如NCSA、PSC、SDSC、NICS）。另一个极端包括高度分布式的协作资源联盟，以NSF项目的紧密耦合和松散耦合联盟为代表，包括但不限于GENI、XSEDE、FutureGrid和NSFCloud，其中包括大学校园IT和校园研究网络。在第二种模式中，一小部分资源由大量参与的站点拥有和运营。CI平台最重要的贡献不是任何一个设施的大量资源，而是整个联盟的广泛覆盖范围。这些分散的联盟有许多令人满意的特点：它们受益于研究人员和数据的自然地理位置，它们需要每个站点相对适度的资源贡献，从而鼓励广泛参与。建立和维护高度分散的网络基础设施联盟涉及不同的技术挑战，需要讨论、分析和克服。该提案资助了一个研讨会，该研讨会将汇集来自GENI、NSFCloud、FutureGrid和XSEDE社区的参与者，讨论、比较/对比并了解不同社区对CI控制框架的需求和方法。研讨会将于2014年10月14日至15日在华盛顿特区举行。为了帮助确定合作机会，我们将特别鼓励参与者就以下主题以“我的项目需要”或“我的项目可以提供”的形式进行陈述：网络基础设施支持研究人员的工具；2. 网络基础设施拥有人/供应商的工具；3. 控制资源的数据结构和协议；和4。用于控制联邦的数据结构和协议。