FDD Massive MIMO

Deep-Learning Aided Channel Training and Precoding in FDD Massive MIMO with Channel Statistics Knowledge

We propose a method for channel training and precoding in FDD massive MIMO based on deep neural networks, exploiting Downlink channel covariance knowledge. IEEE International Conference on Communications (ICC) 2023.

FDD massive MIMO via UL/DL channel covariance extrapolation and active channel sparsification

We propose active channel sparsification, a method of training multi-user MIMO Downlink channels in FDD mode with any given pilot length, while maximizing the effective channel matrix rank. IEEE Transactions on Wireless Communications, 2019.