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

点击翻译按钮获取中文摘要

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.