Learning-based Coexistence in Two-tier Heterogeneous Networks with Cognitive Small Cells

We study the coexistence problem in a two-tier heterogeneous network (HetNet) with cognitive small cells. In particular, we consider an underlay HetNet, where the cognitive small base station (C-SBS) is allowed to use the frequency band of the macro cell with an access probability (AP) as long as the C-SBS satisfies a preset interference probability (IP) constraint at macro user (MUs). To enhance the AP of the C-SBS, we propose that the C-SBS exploits the distance information between the macro base station (MBS) and MUs, namely, MBS-MU distance information, which is contained in the signals of the MBS. Briefly, we first enable the C-SBS to analyze the signal from the MBS to the MU on a target frequency band, and learn the MBS-MU distance information. Then, we calculate the upper bound of the probability that the C-SBS may interfere with the MU, and design an AP with a closed-form expression under the IP constraint at the MU. Numerical results indicate that the proposed algorithm outperforms the state of arts, i.e., up to $90\%$ AP improvement.