Research Infrastructure: CC* Data Storage: Broadening UMBCs Data Storage footprint to Advance Scientific Research and Discovery

寻回研究存储系统R-RSTOR使UMBC的研究人员和合作者能够解决大气科学方面的重要研究，分析极地冰盖，并开发用于人类和机器人交互的人工智能模型。该系统支持加强与马里兰大学环境科学中心（UMCES）在切萨皮克湾及其流域生态研究方面的合作，并通过开放科学数据联盟提供更广泛的社区访问。利用开源Ceph文件系统，它提供了一个灵活的，高性能的，具有成本效益的，可扩展的文件架构，这将使我们能够大大扩展分配给所有教师进行研究。该系统集成了UMBC现有的高性能计算设施和科学DMZ，以简化跨学科和机构间的合作。R-RSTOR旨在利用低延迟非易失性存储器（NVME）组件和大型多pb固态磁盘，以降低与数据操作和传输相关的复杂性和成本，从而缩短研究时间。Ceph文件系统使研究人员能够在单个系统中处理文件、块和基于对象的文件结构。通过在系统上运行的额外网关，研究人员可以利用应用程序编程接口（api）来增强内部部署和云环境之间的数据移动性，适应随着更多工作负载转移到混合云模型而不断变化的计算需求。这项由高级网络基础设施办公室颁发的奖项也得到了国家气候发现云（NDC-C）资源的支持。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The Retriever Research Storage System R-RSTOR enables UMBC researchers and collaborators to address important research in atmospheric science, analyze polar ice caps, and develop AI models for human and robotic interactions. The system supports increased collaborations with the University of Maryland Center for Environmental Science (UMCES) on research into the ecology of the Chesapeake Bay and its watershed, as well as broader community access through the Open Science Data Federation. Utilizing the open-source Ceph file system that provides a flexible, high-performance, cost-effective, and scalable file architecture that will allow us to greatly expand allocations for all faculty conducting research.This system integrates with UMBC's existing High-Performance Computing Facility and Science DMZ to streamline interdisciplinary and inter-institutional collaborations. R-RSTOR is designed to utilize low latency non-volatile memory express (NVME) components and large-scale multi-petabyte solid state disc to reduce complexities and costs associated with data manipulation and transfer, which shortens the time to research. The Ceph file system allows researchers the ability to handle file, block, and object-based file structures within a single system. Through the additional gateways running on the system, researchers can utilize application programming interfaces (APIs) for enhanced data mobility between on-premises and cloud environments, accommodating evolving computational requirements as more workloads shift to a hybrid cloud model.This award by the Office of Advanced Cyberinfrastructure is also supported by National Discovery Cloud for Climate (NDC-C) resources.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.