SIM-Assisted End-to-End Co-Frequency Co-Time Full-Duplex System

TL;DR

This paper introduces a SIM-assisted end-to-end learning framework for co-frequency co-time full-duplex systems, significantly reducing self-interference and improving communication performance through electromagnetic neural networks and intelligent metasurfaces.

Contribution

It proposes integrating a stacked intelligent metasurface with an E2E learning-based control method, pioneering wave-domain processing for self-interference suppression in full-duplex systems.

Findings

Significant BER reduction compared to conventional systems

Successful implementation of electromagnetic neural networks for system control

Demonstrated potential for next-generation transceiver design

Abstract

To further suppress the inherent self-interference (SI) in co-frequency and co-time full-duplex (CCFD) systems, we propose integrating a stacked intelligent metasurface (SIM) into the RF front-end to enhance signal processing in the wave domain. Furthermore, an end-to-end (E2E) learning-based signal processing method is adopted to control the metasurface. Specifically, the real metasurface is abstracted as hidden layers of a network, thereby constructing an electromagnetic neural network (EMNN) to enable driving control of the real communication system. Traditional communication tasks, such as channel coding, modulation, precoding, combining, demodulation, and channel decoding, are synchronously carried out during the electromagnetic (EM) forward propagation through the metasurface. Simulation results show that, benefiting from the additional wave-domain processing capability of the SIM, the SIM-assisted CCFD system achieves significantly reduced bit error rate (BER) compared with conventional CCFD systems. Our study fully demonstrates the potential applications of EMNN and SIM-assisted E2E CCFD systems in next-generation transceiver design.