A Deep Learning Mobility Management Approach for RIS-Empowered Millimeter Wave Wireless Systems

This paper focuses on presenting a new deep learning (DL) mobility management approach for reconfigurable intelligent surface (RIS)-empowered millimeter wave wireless system. On the contrary to previously published contributions, we consider a new type of RIS that has a number of active elements capable of sensing the channel. These channel coefficients are fed to the DL algorithm that estimates the optimal phase shifts of all the RIS elements. Interestingly, the presented approach achieves similar results with the ideal case of perfect channel state information knowledge.