EAGER: ML-enabled Early Warning of Blockage and Beam Transitions in Mobile, Hybrid Sub-6GHz/mmWave Systems
Hans D. Hallen
Project runs from 08/15/2021 to 07/31/2022
Utilization of millimeter-wave (mmWave) frequencies in 5G cellular systems can greatly boost the data rates relative to 4G systems. However, coverage, reliability, and resiliency of mmWave communications can get severely impaired by increased path loss, susceptibility to blockage, and stronger directionality of mmWave signals relative to sub-6 GHz signals as observed in early commercial deployments of 5G mmWave networks. This project evaluates feasibility of a novel, potentially transformative approach to early warning of blockages and beam transitions at mmWave using sub-6GHz observations. Suitability of machine learning (ML) for enabling this task is investigated. A realistic physics-based propagation model is enhanced to validate the proposed approaches. The project is strengthened by the interdisciplinary PI team with combined expertise in communication theory, signal processing, and propagation modeling.