Beam Management with Orientation and RSRP using Deep Learning for Beyond 5G Systems

Beam management (BM), i.e., the process of finding and maintaining a suitable transmit and receive beam pair, can be challenging, particularly in highly dynamic scenarios. Side-information, e.g., orientation, from on-board sensors can help in the user equipment (UE) BM. In this work, we use the orientation information coming from inertial measurement unit (IMU) for effective BM. We use a data-driven strategy and fuse the reference signal received power (RSRP) information with orientation information using an artificial neural network (ANN). Simulation results show that the proposed strategy performs better than the conventional BM and an orientation-assisted BM strategy that utilizes particle filter in another study. Specifically, the proposed data-driven strategy improves the beam-prediction accuracy up to 34% and reduces mean reference signal received power (RSRP) loss caused by sub-optimal beam-selection by up to 4.2 dB when the UE has fast rotation speed.