Due to the very narrow beam used in millimeter wave communication (mmWave), beam alignment (BA) is a critical issue. In this work, we investigate the issue of mmWave BA and present a novel beam alignment scheme on the basis of a machine learning strategy, Bayesian optimization (BO). In this context, we consider the beam alignment issue to be a black box function and then use BO to find the possible optimal beam pair. During the BA procedure, this strategy exploits information from the measured beam pairs to predict the best beam pair. In addition, we suggest a novel BO algorithm based on the gradient boosting regression tree model. The simulation results demonstrate the spectral efficiency performance of our proposed schemes for BA using three different surrogate models. They also demonstrate that the proposed schemes can achieve spectral efficiency with a small overhead when compared to the orthogonal match pursuit (OMP) algorithm and the Thompson sampling-based multi-armed bandit (TS-MAB) method.
A novel sparse array synthesis method for non-uniform planar arrays is proposed, which belongs to compressive sensing (CS)-based systhesis. Particularly, we propose an off-grid refinement technique to simultaneously optimize the antenna element positions and excitations with a low complexity, in response to the antenna position optimization problem that is difficult for standard CS. More importantly, we take into account the minimum inter-element spacing constraint for ensuring the physically realizable solution. Specifically, the off-grid Orthogonal Match Pursuit (OMP) algorithm is first proposed with low complexity and then off-grid Look Ahead Orthogonal Match Pursuit (LAOMP) is designed with better synthesis performance but higher complexity. In addition, simulation results have shown the proposed schemes have more advantages in computational complexity and synthesis performances compared with the related method.