A Compute&Memory Efficient Model-Driven Neural 5G Receiver for Edge AI-assisted RAN

TL;DR

This paper introduces a low-complexity, model-driven neural network receiver for 5G RAN edge deployment, achieving high performance with significantly reduced compute and memory requirements, suitable for scalable 6G systems.

Contribution

It presents a novel neural network-based receiver that is computationally efficient, adaptable to various 5G NR configurations, and does not require retraining for different setups.

Findings

Outperforms state-of-the-art methods in TBLER

Reduces FLOPs by 66 times

Decreases learnable parameters by 396 times

Abstract

Artificial intelligence approaches for base-band processing for radio receivers have demonstrated significant performance gains. Most of the proposed methods are characterized by high compute and memory requirements, hindering their deployment at the edge of the Radio Access Networks (RAN) and limiting their scalability to large bandwidths and many antenna 6G systems. In this paper, we propose a low-complexity, model-driven neural network-based receiver, designed for multi-user multiple-input multiple-output (MU-MIMO) systems and suitable for implementation at the RAN edge. The proposed solution is compliant with the 5G New Radio (5G NR), and supports different modulation schemes, bandwidths, number of users, and number of base-station antennas with a single trained model without the need for further training. Numerical simulations of the Physical Uplink Shared Channel (PUSCH) processing show that the proposed solution outperforms the state-of-the-art methods in terms of achievable Transport Block Error Rate (TBLER), while reducing the Floating Point Operations (FLOPs) by 66$\times$, and the learnable parameters by 396$\times$.