# Time-Sequence Channel Inference for Beam Alignment in Vehicular Networks

## TL;DR

This paper introduces a learning-based method for vehicle-to-infrastructure beam alignment that predicts optimal beam directions using sequence-to-sequence neural networks, significantly reducing overhead and improving performance.

## Contribution

It presents a novel sequence-to-sequence neural network approach to infer future beam directions, reducing channel training overhead in vehicular networks.

## Key findings

- Achieves 8.86% improvement over location-based schemes.
- Maintains within 4.93% of genie-aided optimal performance.
- Reduces channel acquisition and beam training overhead.

## Abstract

In this paper, we propose a learning-based low-overhead beam alignment method for vehicle-to-infrastructure communication in vehicular networks. The main idea is to remotely infer the optimal beam directions at a target base station in future time slots, based on the CSI of a source base station in previous time slots. The proposed scheme can reduce channel acquisition and beam training overhead by replacing pilot-aided beam training with online inference from a sequence-to-sequence neural network. Simulation results based on ray-tracing channel data show that our proposed scheme achieves a $8.86\%$ improvement over location-based beamforming schemes with a positioning error of $1$m, and is within a $4.93\%$ performance loss compared with the genie-aided optimal beamformer.