Adaptive Sector Splitting based on Channel Charting in Massive MIMO Cellular Systems

We consider a downlink scenario where a multiantenna base station in a sectorized cellular system creates multiple logical cells in each sector, applying Adaptive Sector Splitting (ASS). In ASS, a population of User Equipments (UEs) is grouped based on radio Channel State Information (CSI), groups are assigned to cells, and the virtual antennas serving the cells are optimized based on CSI. Grouping UEs based on covariance matrix similarity may result in considerable spatial overlap of the UE groups, and a need for frequent handovers for mobile UEs. To reduce handovers, an improved grouping strategy that takes into account UE physical locations is needed. We use Channel Charting (CC) to learn the radio map of the cell from uplink CSI, and consider UE grouping based on CC locations aiming to maximize the mean distance of UEs to virtual cell borders without the need to know the physical locations of the UEs. Simulation results show that ASS groups based on CC are more compact than angle-of-arrival and covariance matrix based groupings from the literature.