Feng, B; Feng, C; Wong, KK; Quek, TQS; (2025) Deep Unfolding Neural Networks for Fluid Antenna-Enhanced Vehicular Communication. IEEE Transactions on Vehicular Technology 10.1109/TVT.2025.3559786. (In press).

Preview

Text Deep_Unfolding_Neural_Networks_for_Fluid_Antenna-Enhanced_Vehicular_Communication.pdf - Accepted Version Download (1MB) | Preview

Abstract

Fluid antenna (FA) technology has emerged as a promising technology to achieve higher spectral and energy efficiency by introducing a new dimension. However, the antenna position configuration inevitably increases computational complexity, presenting challenges under real-time configuration requirements, especially in vehicular communication systems characterized by rapidly time-varying channels. To address these issues, this paper investigates the classical weighted sum rate maximization problem and proposes an optimization-empowered neural network framework designed to accelerate convergence without compromising accuracy. Extensive simulations demonstrate that the proposed approach effectively mitigates the computational burdens associated with FAs, delivering superior performance in terms of convergence rate and system performance, thus paving the way for the deployment of next-generation FA-enabled communication systems.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item