Distributed Learning Assisted Fronthaul Compression for Multi-Antenna C-RAN

Aymen Askri,Ghaya Rekaya-Ben Othman,Chao Zhang

doi:10.1109/access.2021.3104660

Aymen Askri, Ghaya Rekaya-Ben Othman + Show 1 more

Open Access

https://doi.org/10.1109/access.2021.3104660

Copy DOI

Abstract

This paper investigates the uplink reception in the cloud radio access network (C-RAN), sometimes called centralized-RAN. C-RAN is an architecture for cellular networks which consists of many remote radio units (RRUs) connected to a central processor (CP). Due to the prohibitive complexity of computations, the most efficient uplink C-RAN schemes are challenging to be implemented in practical systems. Using deep neural networks (DNNs), we propose a new and low complex method for uplink C-RAN subject to some quantization rules. This is the first work that uses DNNs to mimic the C-RAN system to the best of our knowledge. Our architecture’s objective, called QDNet, is to jointly optimize the processing done at the RRUs, which considers the quantization constraints and the processing done at the CP side. Inspired by the projected gradient descent algorithm, QDNet is designed as a distributed DNN with sparse connections. The performance of QDNet is compared to current solutions such as the zero-forcing (ZF) equalizer and the sphere decoder (SD). In some scenarios, experiment results show that our scheme achieves 2 dB SNR gain over the linear ZF with the same or lower computational complexity. It also achieves near-optimal performance compared to the SD algorithm, especially for low-to-moderate fronthaul link capacity and many RRUs in the C-RAN system.

Highlights

A S the extensive use of advanced wireless devices and video streaming, smaller size cellular networks emerge to meet the increasing data rates demand
Cloud radio access network (C-RAN) [1] has been seen as a valuable model to cope with the dominant inter-cell interference (ICI) by enabling the joint precoding in the downlink transmission and the joint decoding in the uplink reception at the central processor (CP) side [2]–[4]
The challenge is to design a distributed neural network (NN) which is jointly optimized at the remote radio units (RRUs) and the CP

Summary

Introduction

A S the extensive use of advanced wireless devices and video streaming, smaller size cellular networks emerge to meet the increasing data rates demand. Cloud radio access network (C-RAN) [1] has been seen as a valuable model to cope with the dominant ICI by enabling the joint precoding in the downlink transmission and the joint decoding in the uplink reception at the central processor (CP) side [2]–[4]. A C-RAN model comprises a baseband unit (BBU) pool, RRU networks, and a transportation network called fronthaul. The BBU pool is shared and statically assigned to RRUs. With high computational and storage capabilities, the BBU is centralized and liable to manage processing resources for RRU networks that connect various wireless devices

Objectives

Methods

Findings

Conclusion