Learning Based User Scheduling in Reconfigurable Intelligent Surface Assisted Multiuser Downlink

TL;DR

This paper proposes a novel approach using graph neural networks to optimize user scheduling, RIS configuration, and beamforming in RIS-assisted downlink networks, reducing pilot overhead and improving efficiency.

Contribution

It introduces a GNN-based method for joint user scheduling, RIS configuration, and beamforming that bypasses traditional channel estimation, enabling efficient operation with limited pilots.

Findings

GNN-based scheduling outperforms conventional methods in pilot efficiency.

The approach generalizes to systems with varying numbers of users.

Numerical results demonstrate improved throughput and fairness.

Abstract

Reconfigurable intelligent surface (RIS) is capable of intelligently manipulating the phases of the incident electromagnetic wave to improve the wireless propagation environment between the base-station (BS) and the users. This paper addresses the joint user scheduling, RIS configuration, and BS beamforming problem in an RIS-assisted downlink network with limited pilot overhead. We show that graph neural networks (GNN) with permutation invariant and equivariant properties can be used to appropriately schedule users and to design RIS configurations to achieve high overall throughput while accounting for fairness among the users. As compared to the conventional methodology of first estimating the channels then optimizing the user schedule, RIS configuration and the beamformers, this paper shows that an optimized user schedule can be obtained directly from a very short set of pilots using a GNN, then the RIS configuration can be optimized using a second GNN, and finally the BS beamformers can be designed based on the overall effective channel. Numerical results show that the proposed approach can utilize the received pilots more efficiently than the conventional channel estimation based approach, and can generalize to systems with an arbitrary number of users.