Study on Downlink CSI compression: Are Neural Networks the Only Solution?

TL;DR

This paper compares traditional PCA-based methods with neural network approaches for downlink CSI compression in massive MIMO systems, showing PCA achieves comparable performance without the complexity and generalization issues of neural networks.

Contribution

The study demonstrates that PCA-based CSI compression can match neural network performance, offering a simpler and more generalizable alternative.

Findings

PCA achieves similar reconstruction accuracy to neural network models.

PCA-based method reduces complexity and improves generalization.

Traditional PCA can be a viable alternative to AI/ML methods for CSI compression.

Abstract

Massive Multi Input Multi Output (MIMO) systems enable higher data rates in the downlink (DL) with spatial multiplexing achieved by forming narrow beams. The higher DL data rates are achieved by effective implementation of spatial multiplexing and beamforming which is subject to availability of DL channel state information (CSI) at the base station. For Frequency Division Duplexing (FDD) systems, the DL CSI has to be transmitted by User Equipment (UE) to the gNB and it constitutes a significant overhead which scales with the number of transmitter antennas and the granularity of the CSI. To address the overhead issue, AI/ML methods using auto-encoders have been investigated, where an encoder neural network model at the UE compresses the CSI and a decoder neural network model at the gNB reconstructs it. However, the use of AI/ML methods has a number of challenges related to (1) model complexity, (2) model generalization across channel scenarios and (3) inter-vendor compatibility of the two sides of the model. In this work, we investigate a more traditional dimensionality reduction method that uses Principal Component Analysis (PCA) and therefore does not suffer from the above challenges. Simulation results show that PCA based CSI compression actually achieves comparable reconstruction performance to commonly used deep neural networks based models.