NeTS: JUNO2: Resilient Edge Cloud Designed Networks

为智能和互联社区（SCC）实现可信赖的IoT（物联网）和CPS（网络物理系统）既是一个重要目标，也是一个重大挑战。该项目的目标是通过利用弹性边缘云网络来解决这一挑战——计算能力联网在一起，靠近最终用户和关键应用程序——实现快速响应、对大量应用程序的可扩展性和故障安全操作。该项目将与日本的合作者在弹性边缘云网络上进行协作和基础研究，以实现对未来网络基础科学的基本理解。该方法包括虚拟化自适应计算和网络，考虑资源约束，终端设备/传感器的潜在移动性和安全性。该项目的成果将为SCC应用（如智能健康、智能交通、智能能源等）推进更具弹性的网络计算基础设施。日美合作为示范项目方法提供了一个国际测试平台。本项目旨在通过实现弹性分布式边缘云网络架构，提高IoT/CPS的性能。目标是提供(1)通过在终端设备上引入时空浮动边缘云（EC）功能来扩展覆盖范围；(2)通过接口多样性和基于流量的控制实现终端设备与边缘云之间的弹性通信；(3)优化终端设备、EC和后端云（BC）之间的资源分配，以满足不同的服务质量需求，如延迟和阻塞率；(4)设计一种时空优化、动态可调的虚拟网络链路和虚拟机利用方式；(5)保护IoT/CPS设备的仿生入侵检测系统；(5)利用超立方体技术构建分布式数据库。该项目将利用纽约的SmartCity测试平台和日本的StarBED4测试平台，后者是一个由1000台服务器组成的大规模仿真/仿真基础设施。这些将集成到一个单一的测试平台上进行大规模的真实和模拟实验，并将对美国和日本的研究人员进行该项目的访问。这些网络将通过全球研究网络，即美国的Internet2和NYSERNET，以及日本的JGN和SINET连接起来。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。

Achieving trustworthy IoT(Internet of Things) and CPS(Cyberphysical Systems) for Smart and Connected Communities (SCC) is both an important goal and a major challenge. The objective of this project is to address that challenge by leveraging a resilient edge cloud network--computing capabilities that are networked together and reside close to the end user and critical applications -- to enable fast response, scalability to a large number of applications, and fail-safe operation. The project will conduct collaborative and foundational research with collaborators in Japan, on a resilient edge cloud network to achieve basic understanding of the underlying science for future networks. The approach includes virtualized adaptable computing and networking, consideration of resource constraints, potential mobility of end devices/sensors and security. The results from this project will advance more resilient network-compute infrastructure for SCC applications such as smart health, smart transportation, smart energy, etc. The Japanese-US collaboration provides an international testbed for demonstrating the project approach. This project aims to improve the performance of IoT/CPS by realizing a resilient distributed edge cloud network architecture. The objective is to provide (1) coverage extension by introducing spatio-temporal floating edge cloud (EC) function over end devices; (2) resilient communication between end-devices and edge clouds via interface diversity and flow-based control; (3) optimal resource allocation among end-device, EC, and backend cloud (BC) to meet diverse quality-of-service requirements such as latency and blocking rate; (4) designing a spatially and temporally optimized and dynamically adjustable utilization of virtual network links and virtual machines (5) bio-inspired intrusion detection system for protecting IoT/CPS devices (5) distributed database using hypercube. The project will leverage the SmartCity testbed in New York and the StarBED4 testbed in Japan, which is a large-scale emulation/simulation infrastructure consisting of 1,000 servers. These will be integrated into a single testbed for large-scale real and emulation experiments, and will be accessible to both US and Japanese researchers on this project. The networks will be connected via global research networks i.e., Internet2 and NYSERNET in US, and JGN and SINET in Japan.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.