Generative vs. Predictive Models in Massive MIMO Channel Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Ju-Hyung, Lee, Joohan, Molisch, Andreas F.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915035247280128
author Lee, Ju-Hyung
Lee, Joohan
Molisch, Andreas F.
author_facet Lee, Ju-Hyung
Lee, Joohan
Molisch, Andreas F.
contents Massive MIMO (mMIMO) systems are essential for 5G/6G networks to meet high throughput and reliability demands, with machine learning (ML)-based techniques, particularly autoencoders (AEs), showing promise for practical deployment. However, standard AEs struggle under noisy channel conditions, limiting their effectiveness. This work introduces a Vector Quantization-based generative AE model (VQ-VAE) for robust mMIMO cross-antenna channel prediction. We compare Generative and Predictive AE-based models, demonstrating that Generative models outperform Predictive ones, especially in noisy environments. The proposed VQ-VAE achieves up to 15 [dB] NMSE gains over standard AEs and about 9 [dB] over VAEs. Additionally, we present a complexity analysis of AE-based models alongside a diffusion model, highlighting the trade-off between accuracy and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16971
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative vs. Predictive Models in Massive MIMO Channel Prediction
Lee, Ju-Hyung
Lee, Joohan
Molisch, Andreas F.
Information Theory
Networking and Internet Architecture
Massive MIMO (mMIMO) systems are essential for 5G/6G networks to meet high throughput and reliability demands, with machine learning (ML)-based techniques, particularly autoencoders (AEs), showing promise for practical deployment. However, standard AEs struggle under noisy channel conditions, limiting their effectiveness. This work introduces a Vector Quantization-based generative AE model (VQ-VAE) for robust mMIMO cross-antenna channel prediction. We compare Generative and Predictive AE-based models, demonstrating that Generative models outperform Predictive ones, especially in noisy environments. The proposed VQ-VAE achieves up to 15 [dB] NMSE gains over standard AEs and about 9 [dB] over VAEs. Additionally, we present a complexity analysis of AE-based models alongside a diffusion model, highlighting the trade-off between accuracy and computational efficiency.
title Generative vs. Predictive Models in Massive MIMO Channel Prediction
topic Information Theory
Networking and Internet Architecture
url https://arxiv.org/abs/2411.16971