CC*DNI Networking Infrastructure: Washington University Research Network (WURN)

CC*DNI 网络基础设施：华盛顿大学研究网络 (WURN)

• 批准号: 1541364
• 负责人: Roch Guerin
• 金额: $ 47.56万
• 依托单位: Washington University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-10-01 至 2017-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1541364&HistoricalAwards=false
• 关键词: CC; DNI; Networking; Infrastructure; Washington

New discoveries in science and engineering research in the 21st century arise from the creation, analysis and communication of staggering amounts of data. Researchers at Washington University in St. Louis (WUSTL) are at the forefront of Big Data research and thus continually pushing the university's network infrastructure. The creation of the Washington University Research Network is a critical step forward in providing the necessary hardware and software capabilities to enable Petabytes of data to move into and out of university systems. However, the capability of genomics, imaging and planetary science (to name a few) instruments to generate new data is increasing exponentially and can quickly outpace the capacity of any network. The project creates a Software Defined Network (SDN) based distributed Science DMZ network on the WUSTL campus across three existing data centers linked to each other and research and education wide area network connections via dedicated 40Gbps hardware in the existing campus core. The key contribution of this project is to deploy new techniques in SDN that optimize the way existing and future capacity is utilized, while also ensuring the necessary monitoring oversight needed for predictable and secure operation. By scheduling large data transfers and intelligently partitioning and sharing network capacity, the project's goal is to ensure near optimal utilization of resources and provide a cost effective solution. Network programmability is also leveraged to dynamically instantiate monitoring resources that oversee the security of those transfers.

世纪科学和工程研究的新发现来自于对惊人数量的数据的创建、分析和交流。 圣路易斯华盛顿大学（WUSTL）的研究人员处于大数据研究的前沿，因此不断推动大学的网络基础设施。 华盛顿大学研究网络的建立是向前迈出的关键一步，它提供了必要的硬件和软件能力，使PB级的数据能够进出大学系统。 然而，基因组学、成像和行星科学（仅举几例）仪器生成新数据的能力正在呈指数级增长，并可能迅速超过任何网络的能力。该项目在WUSTL校园内创建了一个基于软件定义网络（SDN）的分布式科学DMZ网络，该网络跨越三个相互连接的现有数据中心，并通过现有校园核心中的专用40Gbps硬件连接研究和教育广域网。该项目的主要贡献是在SDN中部署新技术，优化现有和未来容量的利用方式，同时确保可预测和安全运营所需的必要监控监督。 通过调度大型数据传输和智能分区和共享网络容量，该项目的目标是确保接近最佳的资源利用率，并提供一个具有成本效益的解决方案。 还利用网络可编程性来动态地实例化监视这些传输的安全性的监视资源。