Millimeter Wave Communications on Overhead Messenger Wire: Deep Reinforcement Learning-Based Predictive Beam Tracking

Abstract

This paper discusses the feasibility of beam tracking against dynamics in millimeter wave (mmWave) nodes placed on overhead messenger wires. As specific disturbances in on-wire deployments, we consider wind-forced perturbations and disturbances caused by impulsive forces to wires. Our contribution is to answer whether the historical positions/velocities of a mmWave node are useful to track directional beams, given the complicated on-wire dynamics. To this end, we implement deep reinforcement learning (DRL) to learn the relationships between the historical positions/velocities and appropriate beam-steering angles. Our numerical evaluations yielded the following key insights: First, against wind perturbations, an appropriate beam-tracking policy can be learned from the historical positions/velocities of a node. Second, against impulsive forces to the wire, the use of the position/velocity of the node is not necessarily sufficient, owing to the rapid node displacement. To resolve this, we propose taking advantage of the positional interaction on the wire. This is done by leveraging the positions/velocities of several points on the wire as state information in DRL. The results confirmed the avoidance of beam misalignment due to impulsive forces, which was not possible using only the position/velocity of the node.