Machine Learning-based Channel Prediction in Wideband Massive MIMO Systems with Small Overhead for Online Training

TL;DR

This paper tackles channel prediction in wideband massive MIMO under dynamic environments by introducing an online re-training framework. It introduces aggregated learning (AL) to pre-process and augment limited training data, with AL-AD and AL-FD variants exploiting array- and frequency-domain views of MIMO-OFDM channels. Empirical results show AL-FD consistently yields the best NMSE and sum-rate performance while requiring minimal data-collection time, supported by analyses of Type-I/II and temporal correlations. The approach is architecture-agnostic and adaptable to various neural networks, offering a practical path toward robust, low-overhead online channel prediction in future wireless systems.

Abstract

Channel prediction compensates for outdated channel state information in multiple-input multiple-output (MIMO) systems. Machine learning (ML) techniques have recently been implemented to design channel predictors by leveraging the temporal correlation of wireless channels. However, most ML-based channel prediction techniques have only considered offline training when generating channel predictors, which can result in poor performance when encountering channel environments different from the ones they were trained on. To ensure prediction performance in varying channel conditions, we propose an online re-training framework that trains the channel predictor from scratch to effectively capture and respond to changes in the wireless environment. The training time includes data collection time and neural network training time, and should be minimized for practical channel predictors. To reduce the training time, especially data collection time, we propose a novel ML-based channel prediction technique called aggregated learning (AL) approach for wideband massive MIMO systems. In the proposed AL approach, the training data can be split and aggregated either in an array domain or frequency domain, which are the channel domains of MIMO-OFDM systems. This processing can significantly reduce the time for data collection. Our numerical results show that the AL approach even improves channel prediction performance in various scenarios with small training time overhead.

Figures (16)

• Figure 1: A massive MIMO system consisting of a BS with $M_\text{BS}$ antennas and a UE with $M_\text{UE}$ antennas, where the estimated channels can be outdated due to the mobility of the UE.
• Figure 2: Overall process of online re-training framework.
• Figure 3: Overall process of the AL approach.
• Figure 4: Type-I correlation of the array domain channels and frequency domain channels.
• Figure 5: Type-II correlation of the array domain channels and frequency domain channels.