Collaborative Research: NeTS: JUNO3: End-to-end network slicing and orchestration in future programmable converged wireless-optical networks

超越5G/6G和下一代核心网络承诺广泛的新应用和工业垂直领域，如数字企业，工业4.0和智慧城市。为了及时实现端到端性能保障，实现这一前所未有的机遇，需要在接入前传、边缘云、核心网等各个领域实现革命性的技术突破。为了实现这一目标，必须克服若干挑战。首先，新兴的应用程序通常需要用于关键任务的高可用性和可靠性。其次，边缘到边缘流量逐渐主导传统的云到用户流量，改变了流量模式和形态。第三，云服务带来的互联网和核心网流量的爆炸式增长，以及新冠肺炎疫情后的“新常态”，推动了新型可编程宽带数据传输。最后，无缝的端到端网络和管理对于支持数据密集型、延迟敏感的应用程序（如元宇宙、数字孪生和远程手术）是必要的。本项目旨在解决这些挑战。这项美日联合项目的目标是开发关键的使能器，以实现5G/6G以上应用的全频谱。具体目标是：a)设计基于新型光纤供电技术的弹性前传架构，以提供无线接入的生存能力；b（利用机器学习技术和马尔可夫决策过程设计自动边缘云管理和服务链部署；c）设计多pb光核心网络和高效的访问边缘核心编排和切片，以实现严格的服务水平协议；d)对无线光网络测试平台进行原型设计，并评估端到端协调性能。该项目带来了美国和日本研究人员独特的研究协同作用，并将奠定端到端网络切片和编排的理论，算法和实验基础，以实现未来可编程融合无线光网络。研究成果将通过光网络、边缘和无线领域的协调，对技术和社会产生全面和变革性的广泛影响。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。

Beyond 5G/6G and next-generation core networks promise a wide range of new applications and industrial verticals such as digital enterprise, Industry 4.0, and smart cities. Revolutionary technological breakthroughs in all domains, including access fronthaul, edge clouds, and core networks, are necessary to realize this unprecedented opportunity through timely end-to-end performance guarantees. Several challenges must be overcome in order to achieve this. Firstly, emerging applications often demand high availability and reliability for mission-critical purposes. Secondly, edge-to-edge traffic flows gradually dominate conventional cloud-to-user flows, transforming traffic patterns and profiles. Thirdly, the explosive growth of the Internet and core network traffic due to cloud services and the “new normal” following the COVID-19 pandemic propel new programmable broadband data delivery. Lastly, seamless end-to-end networking and management are necessary to support data-intensive, latency-sensitive applications such as metaverse, digital twins, and remote surgery. This project seeks to address these challenges. The objective of this joint US-Japan project is to develop critical enablers to realize the full spectrum of beyond 5G/6G applications. The specific aims are to: a) Design resilient fronthaul architectures based on novel power-over-fiber technology to provide wireless access survivability; b(Design automatic edge cloud management and service chain deployment by leveraging machine learning techniques and Markov decision processes; c)Design multi-petabit optical core networks and efficient access-edge-core orchestration and slicing for stringent service-level agreements; d) Prototype a wireless-optical network testbed and evaluate end-to-end harmonization performance. This project brings unique research synergy of US and Japanese researchers and will lay the theoretical, algorithmic, and experimental foundation of end-to-end network slicing and orchestration to enable future programmable converged wireless-optical networks. The research outcomes will have overarching and transformative broader impacts on technology and society through the harmonization of optical networking, edge, and wireless domains.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.