Abstract: To avoid the overload of fronthaul links in cell-free massive multiple input multiple output (MIMO) system, an optimization problem for access point selection is formulated to maximize the fronthaul link usage efficiency. Firstly, the average spectral efficiency per-link is constructed to measure the utilization efficiency of the fronthaul link. Secondly, the objective problem of maximizing the average spectral efficiency per-link while meeting users’ quality of service requirements is established. Then, considering the non-convexity of the objective problem and the non-differentiability of the optimization variables, which makes it challenging for traditional optimization algorithms to find solutions, a dynamic access point selection algorithm based on deep deterministic policy gradient ( DDPG ) is proposed. Finally, the output of the DDPG is refined to ensure compatibility with the discrete nature of access point selection actions. Simulation results show that the proposed algorithm can effectively enhance the average spectral efficiency per link of the system and meet the quality of service requirements.

Key words: massive multiple input multiple output, cell-free network architecture, access point selection, deep deterministic policy gradient