Excellence in Research: Artificial Intelligence Aided Metasurface Design and Application in Next Generation of Cellular Communication Systems

点击翻译按钮获取中文摘要

The radio propagation environment is typically viewed as an uncontrolled and unpredictable aspect in the current wireless communication system paradigm. Because of the unpredictable changes in the radio environment, signal transmission encounters reflections, diffractions, and scattering before arriving at the receiver with numerous copies of attenuated and delayed components. This project will explore how to design an intelligent reflecting surface (IRS) comprised of metamaterials to deploy in the next generation of cellular communication systems to tune the wireless environment and hence achieve intelligent and reconfigurable wireless channels to increase network throughput and energy efficiencies. IRS is typically a flat surface made of a large number of passive reflecting elements (PREs), each of which can generate a regulated change in the amplitude and phase of the incoming signal separately. As a result, electromagnetic waves emanating from the transmitter nodes can be reflected by IRS in a manner that allows them to take advantage of a more favorable propagation environment en route to the reception nodes. By densely deploying IRSs in wireless networks and intelligently coordinating their reflections, wireless systems can increase the likelihood of achieving a line-of-sight (LOS) propagation path between transmitter and receiver nodes while minimizing the impact of co-channel and inter-cell interference and optimizing the energy efficiency of the communication system. However, a successful accomplishment of an IRS-aided communication system requires considering coherent design factors jointly from wireless communications and electromagnetic modeling of devices. The results and analysis conducted in this project will allow electromagnetics, multiphysics, and wireless communication researchers to extend the developed idea to application scenarios.This project will design, develop, and analyze artificial intelligence (AI) driven innovative approaches to address fundamental challenges inherent to baseband signal processing at transmitter and receiver for IRS-aided communication systems. The capability of reconfigurable technologies and novel metasurfaces will be integrated to design and apply new IRS devices by developing a comprehensive and innovative numerical modeling and simulation framework. To enhance the network throughput for an IRS-aided next-generation cellular communication system, cross-functional resource allocation schemes will be proposed by considering design constraints from wireless communications and device physics. Both narrowband and wideband channels will be regarded to conduct this systematic investigation, and novel design approaches will be proposed that perform close to theoretical performance while addressing practical design constraints. The proposed methods will be implemented in a simulation framework and compared with the state-of-the-art approaches to show their effectiveness in wireless communication systems. These research works will encourage efficient system design and algorithm development for the next generation of cellular communication systems and assist product and algorithm engineers and researchers utilizing IRS.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.