I-Corps: Software-Defined Overlay Virtual Private Network for Edge Computing

这个I-Corps项目的更广泛的影响/商业潜力是通过提供一个可扩展的、自组织的、自我修复的虚拟专用网络来实现和支持新兴的物联网（IoT）应用，该网络连接从云到网络边缘的设备。边缘计算包含了越来越多的技术，这些技术可以在传感器和物联网设备的地理位置附近实现数据存储和处理。 该技术为智能城市、制造业、国防、遥感/监控/分析、广告和娱乐等各种新兴应用提供了低延迟响应时间和高吞吐量数据访问的基础。具体而言，该项目将推进有可能降低边缘计算应用程序的开发，部署和管理成本的技术，使现有应用程序能够在不修改的情况下跨位于多个提供商上的地理上分散的异构边缘计算资源进行通信。这些功能将直接惠及系统集成商和/或应用程序开发商，他们构建的产品可以将该服务作为其各自解决方案的一部分并加以利用。I-Corps项目旨在将边缘计算的网络虚拟化技术商业化，该技术建立在自管理和自组织软件定义覆盖网络的研究和开发基础之上。该系统组装其基本抽象（组织为结构化对等覆盖拓扑的互联网隧道的数据平面），然后以对应用透明的方式自主路由虚拟网络流量。其分散的方法已被证明是灵活的，可扩展的，并对故障有弹性。物联网（IoT）类应用或网络物理解决方案展示了严重依赖于分布在多个地理位置的设备和应用之间基于互联网协议（IP）的通信的工作流程。这些环境通常会包含大量异构设备，这些设备具有复杂的、不断发展的网络配置，这些配置对手动管理来说具有挑战性且容易出错-这些挑战由该项目在网络层直接解决。该奖项反映了NSF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 broader impact/commercial potential of this I-Corps project is to enable and support the emerging class of Internet-of-Things (IoT) applications by delivering a scalable, self-organizing, self-healing, virtual private network connecting devices spanning from the cloud to the network's edge. Edge computing encompasses a growing set of technologies that enable data storage and processing within geographic proximity of sensors and IoT devices. This technology provides a foundation of low-latency response times and high-throughput data access for a wide range of emerging applications, such as smart cities, manufacturing, defense, remote sensing/monitoring/analytics, advertising, and entertainment. Specifically, this project will advance technologies that have the potential to lower the cost of development, deployment, and management of edge computing applications by enabling existing applications to communicate without modifications, across a geographically dispersed set of heterogeneous edge computing resources residing on multiple providers. These capabilities are envisioned to be of direct benefit to system integrators and/or application developers who build products that can incorporate and utilize the service as part of their respective solutions.This I-Corps project pursues commercialization of a network virtualization technology for edge computing that builds on the research and development of a self-managing and self-organizing software-defined overlay network. The system assembles its base abstraction (a data-plane of Internet tunnels organized as a structured peer-to-peer overlay topology) and then autonomously routes virtual network traffic in a manner that is transparent to applications. Its decentralized approach has been shown to be flexible, scalable, and resilient to failures. Internet-of-Things (IoT) class applications or cyber-physical solutions exhibit workflows that depend heavily on Internet Protocol (IP) based communications among devices and applications that are distributed across multiple geographic sites. These environments will typically incorporate large numbers of heterogeneous devices that have complex, evolving network configurations that are challenging and error-prone to manually administer - challenges which are directly addressed by this project at the network layer.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.