Traffic-Aware Hierarchical Beam Selection for Cell-Free Massive MIMO

Beam selection for joint transmission in cell-free massive multi-input multi-output systems faces the problem of extremely high training overhead and computational complexity. The traffic-oriented quality of service additionally complicates the beam selection problem. To address this issue, we propose a traffic-aware hierarchical beam selection scheme performed in a dual timescale. In the long-timescale, the central processing unit collects wide beam responses from base stations (BSs) to predict the power profile in the narrow beamspace with a convolutional neural network, based on which the cascaded multiple-BS beamspace is carefully pruned. In the short-timescale, maximization of delay satisfaction rate w.r.t. beam selections within multiple consecutive time slots is modeled as a partially observable Markov decision process (POMDP) and addressed by reinforcement learning. Numerical results demonstrate that the proposed scheme significantly reduces both model training cost and beam training overhead and is more likely to meet the user-specific delay requirement, compared to existing methods.