Optimal number of user antennas in a constrained pilot-length massive MIMO system

In this study, the authors analyse the performance of a massive multiple-input multiple-output network with N-antenna users. Equipping the user terminal (UT) with a multiple of antennas is usually challenging since it increases the overhead of the channel estimation process (linearly with N). In this study, the authors use semi-blind (data-aided) channel estimation that significantly reduces the pilot overhead and analytically obtains the optimal number of antennas that can be mounted at the UT. The proposed channel estimation algorithm is especially useful in cases where a UT can be assigned a single, or generally a few numbers of, pilot sequence(s) although it might have a number of antennas greater than the number of sequences (as the case of 5G proposed solutions); therefore the network does not have to assign more pilots to the user in order to estimate the additional antennas. The authors also characterise the user outage performance when a part of its data is used for the blind channel estimation.