Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kasalaee, Ghazal, Karkan, Ali Hasanzadeh, Frigon, Jean-François, Leduc-Primeau, François
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929713083056128
author Kasalaee, Ghazal
Karkan, Ali Hasanzadeh
Frigon, Jean-François
Leduc-Primeau, François
author_facet Kasalaee, Ghazal
Karkan, Ali Hasanzadeh
Frigon, Jean-François
Leduc-Primeau, François
contents The deployment of deep learning (DL) models for precoding in massive multiple-input multiple-output (mMIMO) systems is often constrained by high computational demands and energy consumption. In this paper, we investigate the compute energy efficiency of mMIMO precoders using DL-based approaches, comparing them to conventional methods such as zero forcing and weighted minimum mean square error (WMMSE). Our energy consumption model accounts for both memory access and calculation energy within DL accelerators. We propose a framework that incorporates mixed-precision quantization-aware training and neural architecture search to reduce energy usage without compromising accuracy. Using a ray-tracing dataset covering various base station sites, we analyze how site-specific conditions affect the energy efficiency of compressed models. Our results show that deep neural network compression generates precoders with up to 35 times higher energy efficiency than WMMSE at equal performance, depending on the scenario and the desired rate. These results establish a foundation and a benchmark for the development of energy-efficient DL-based mMIMO precoders.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08758
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding
Kasalaee, Ghazal
Karkan, Ali Hasanzadeh
Frigon, Jean-François
Leduc-Primeau, François
Signal Processing
Machine Learning
The deployment of deep learning (DL) models for precoding in massive multiple-input multiple-output (mMIMO) systems is often constrained by high computational demands and energy consumption. In this paper, we investigate the compute energy efficiency of mMIMO precoders using DL-based approaches, comparing them to conventional methods such as zero forcing and weighted minimum mean square error (WMMSE). Our energy consumption model accounts for both memory access and calculation energy within DL accelerators. We propose a framework that incorporates mixed-precision quantization-aware training and neural architecture search to reduce energy usage without compromising accuracy. Using a ray-tracing dataset covering various base station sites, we analyze how site-specific conditions affect the energy efficiency of compressed models. Our results show that deep neural network compression generates precoders with up to 35 times higher energy efficiency than WMMSE at equal performance, depending on the scenario and the desired rate. These results establish a foundation and a benchmark for the development of energy-efficient DL-based mMIMO precoders.
title Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2502.08758