Fast Initial Access with Deep Learning for Beam Prediction in 5G mmWave Networks
Tarun S. Cousik, Vijay K. Shah, Jeffrey H. Reed, Tugba Erpek, Yalin E. Sagduyu
Abstract
We present DeepIA, a deep learning solution for a fast, reliable and secure initial access (IA) in directional networks such as the mmWave networks in 5G systems. By utilizing only a subset of beams during the IA process, DeepIA removes the need for an exhaustive beam search thereby reducing the beam sweep time in IA. A deep neural network (DNN) is trained to learn the complex mapping from the received signal strengths (RSSs) collected with a reduced number of beams to the optimal spatial beam of the receiver (among a larger set of beams). In test time, DeepIA measures the RSSs only from a small number of beams and runs the DNN to predict the best beam for IA. We show that DeepIA reduces the IA time by sweeping fewer beams and significantly outperforms the conventional IA's beam prediction accuracy in both line of sight (LoS) and non-line of sight (NLoS) mmWave channel conditions.