ICE-T: RI: A Knowledge-Defined Platform for Real-Time Management of Transmissions and Computations at Network Edge

由于第五代（5G）蜂窝通信系统中的通信和计算的高度动态性质，新服务将需要实时管理以实现通信和计算中的极低延迟。为了推进技术水平，该项目将探索资源管理算法，这些算法借鉴了高频金融交易系统中使用的统计学习、估计和数据驱动技术。该项目将设计和原型化一个基于低成本可编程交换机的平台，使研究人员能够试验基于统计学习的新型算法解决方案，用于边缘网络的实时管理。该平台将有两个主要研究目标：1）探索基于学习的解决方案，用于虚拟路径和虚拟交换机的真实的时间管理; 2）研究核心5G计算和网络资源的实时管理，并在网络边缘协调边缘计算处理。通过利用学习理论，该项目将定义新的抽象和接口，使网络运营商能够在网络边缘协调计算和流量分配决策。该项目将开发新的方法，以了解网络参数预测和计算需求的算法方面的发展。该项目将启动圣刘易斯大学和意大利帕多瓦大学的研究人员之间的新的研究合作。该奖项反映了NSF的法定使命，并被认为是值得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的支持。

Due to the highly dynamic nature of the communications and computations in 5th Generation (5G) cellular communications systems, new services will require real-time management to achieve extremely low latencies in communication and computation. To advance the state of the art, this project explores resource management algorithms that borrow ideas from the use of statistical learning, estimation, and data-driven techniques from high frequency financial trading systems.The project will design and prototype a platform based on low-cost programmable switches that will allow researchers to experiment with novel statistical learning-based algorithmic solutions for real-time management of edge networks. The platform will have two main research objectives: 1) to explore learning based solutions for real time management of virtual paths and virtual switches; and 2) to investigate real-time management of core 5G computation and network resources, and to orchestrate edge computing processing at the network edge. By leveraging learning theory, the project will define new abstractions and interfaces that will allow network operators to coordinate computation and traffic allocation decisions at the network edge. This project will develop novel approaches towards understanding the development of algorithmic aspects of prediction of network parameters and computational needs. This project will initiate a new research collaboration between investigators at Saint Louis University and the University of Padova, Italy.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.