Unsupervised Learning-Based Joint Resource Allocation and Beamforming Design for RIS-Assisted MISO-OFDMA Systems

TL;DR

This paper introduces an unsupervised learning framework for joint resource allocation and beamforming in RIS-assisted MISO-OFDMA systems, significantly reducing computational complexity while maintaining near-optimal performance.

Contribution

It proposes a novel two-stage deep learning approach with BeamNet and AllocationNet for efficient joint design of RIS phase shifts, beamforming, and resource allocation.

Findings

Achieves 99.93% of SCA baseline sum rate

Operates with only 0.036% of baseline runtime

Remains robust across different channel and user scenarios

Abstract

Reconfigurable intelligent surfaces (RIS) are key enablers for 6G wireless systems. This paper studies downlink transmission in an RIS-assisted MISO-OFDMA system, addressing resource allocation challenges. A two-stage unsupervised learning-based framework is proposed to jointly design RIS phase shifts, BS beamforming, and resource block (RB) allocation. The framework includes BeamNet, which predicts RIS phase shifts from CSI, and AllocationNet, which allocates RBs using equivalent CSI derived from BeamNet outputs. Active beamforming is implemented via maximum ratio transmission and water-filling. To handle discrete constraints while ensuring differentiability, quantization and the Gumbel-softmax trick are adopted. A customized loss and phased training enhance performance under QoS constraints. Simulations show the method achieves 99.93% of the sum rate of the SCA baseline with only 0.036% of its runtime, and it remains robust across varying channel and user conditions.