Deep Transfer Learning-Based Downlink Channel Prediction for FDD Massive MIMO Systems

Artificial intelligence (AI) based downlink channel state information (CSI) prediction for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems has attracted growing attention recently. However, existing works focus on the downlink CSI prediction for the users under a given environment and is hard to adapt to users in new environment especially when labeled data is limited. To address this issue, we formulate the downlink channel prediction as a deep transfer learning (DTL) problem, and propose the direct-transfer algorithm based on the fully-connected neural network architecture, where the network is trained in the manner of classical deep learning and is then fine-tuned for new environments. To further improve the transfer efficiency, we propose the meta-learning algorithm that trains the network by alternating inner-task and across-task updates and then adapts to a new environment with a small number of labeled data. Simulation results show that the direct-transfer algorithm achieves better performance than the deep learning algorithm, which implies that the transfer learning benefits the downlink channel prediction in new environments. Moreover, the meta-learning algorithm significantly outperforms the direct-transfer algorithm, which validates its effectiveness and superiority.

I. Introduction

The acquisition of downlink channel state information (CSI) is a very challenging task for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems due to the prohibitively high overheads associated with downlink training and uplink feedback [1]–[3]. By exploiting the angular and delay reciprocities between the uplink and the downlink [4]–[6], conventional methods proposed to reduce the downlink training overhead by extracting frequency-independent information from the uplink CSI, or to reduce the uplink feedback overhead by using compressive sensing based algorithms [7]–[10]. Nevertheless, the conventional methods either assume that the propagation paths are distinguishable and limited or highly rely on the sparsity of channels.