Online Switch-Based Hybrid Beamforming for Massive MIMO Systems

Abstract

Switch-based hybrid beamforming is a low-cost solution for implementing the analog segment of a hybrid beam-forming network. Although an analog beamformer comprising a network of switches allows low hardware complexity, designing such a network is computationally expensive. In this paper, we consider a single user massive multiple-input multiple-output (MIMO) system and propose a low computational complexity method for designing a switch-based hybrid precoder that maximizes the mutual information. We propose a method wherein the analog beamformer is approximated after solving a convex (concave) problem and employing low-rank matrix decomposition. Then, considering a sequence of channel realizations we frame the intermediate convex problem as an online convex optimization (OCO) and give the conditions under which the online version approaches the solution of the primary convex problem after some iterations by learning from previous steps. We finally study the performance through numerical results and demonstrate that the proposed online method offers a low complexity solution that tracks the spectral efficiency delivered by fully digital beamformer, and converges to the solution provided by direct maximization of the intermediate problem.