Generative vs. Predictive Models in Massive MIMO Channel Prediction

TL;DR

This paper compares generative and predictive autoencoder models for massive MIMO channel prediction, introducing a VQ-VAE that outperforms standard models especially under noisy conditions, with significant NMSE improvements.

Contribution

The paper introduces a VQ-VAE model for robust MIMO channel prediction and demonstrates its superiority over predictive models in noisy environments.

Findings

VQ-VAE achieves up to 15 dB NMSE gains over standard AEs.

Generative models outperform predictive models in noisy scenarios.

Complexity analysis highlights trade-offs between accuracy and computational efficiency.

Abstract

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.