Adaptive SVM-based Beam Allocation for MmWave Small Cell Networks

Robust mmWave beamforming for high-speed mobile communications (i.e. the vehicular communications with Gbps links) is a challenging task, since its susceptibility to blockage and possible multi-cell interference. Toward this end, based on machine learning, we propose a data-driven method of mmWave beam selection in multi-cell systems to achieve a near-optimal fast beam allocation with low complexity. In particular, an online learning algorithm based on SVM equipped with the RBF kernel, namely SVM-based online beam selection (SBOS) algorithm is proposed. The proposed algorithm starts with an adaptive beam selection process for certain traffic pattern that uses a support vector machine (SVM) learning model to adaptively refine the beam selection strategy. Furthermore, the extensive simulation results show that the proposed algorithm achieves a better performance versus UCB and Random methods. Overall, the proposed approach offers new capabilities to design the active beam selection learning for handling multi-cell interference, especially in facilitating future mmWave vehicle communications.