Collaborative Research: SWIFT: Enabling Intelligent Pinpoint Space-Spectrum Utilization and Sharing

未来几代通信系统必须支持大量具有不同优先级的高效共享频谱的移动设备。为了满足这种需求，本项目超越了传统的多天线通信技术，探索了一种新的无线设计范例，除了考虑频谱外，还考虑了信号的空间特性。这项研究旨在提高数据速率并实现高效的频谱共享，从而使5G和6G通信系统以及传统系统受益。越来越明显的是，作为国家关键基础设施的一部分，高效和高速的通信系统有助于提高社会生产力和保持国家的竞争优势。为了实现上述目标，该项目的主要任务是：1)估计和了解构成多径网络的节点之间可能的空间信号传输路径；2)进行信号路径选择、编码、广播和多址传输的跨层设计；3)使用软件定义的无线电对多径网络进行实验验证。机器学习辅助算法将被设计成通过利用重复模式来学习多路径网络。将采用优化和编码来共同选择信号传输方向和设计发射信号，从而实现频谱的有效共享。预期成果是通过在空间中密集重用频率来高效利用和共享频谱的方法。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

Future generations of communication systems must support vast numbers of mobile devices that share the spectrum efficiently with different priorities. To meet such a demand, this project goes beyond the traditional techniques of multi-antenna communications and explores a novel paradigm of wireless design by considering the spatial characteristics of signals, in addition to spectrum. This research aims to increase data rates and enable efficient spectrum sharing that could benefit 5G and 6G communication systems, as well as legacy systems. It is increasingly evident that efficient and high-speed communication systems, which are part of the nation's critical infrastructure, help improve society's productivity and maintain the nation's competitive edge. The project will also help train the workforce for the high-tech communication industry.For achieving the above goal, the key tasks of the project are 1) to estimate and learn the possible spatial signal transmission paths between nodes that form the multipath network, 2) to perform cross-layer design of signal paths selection, coding, broadcast and multiaccess transmissions, 3) and to undertake an experimental verification of the multipath network using software defined radios. Machine learning assisted algorithms will be designed to learn the multipath networks by taking advantage of the repeated patterns. Optimization and coding will be employed to jointly select signal transmission directions and design transmit signals so that the spectrum can be efficiently shared. The expected outcomes are methods for highly effective utilization and sharing of spectrum via a dense reuse of frequency across space.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.