Joint Optimization of Data- and Model-Driven Probing Beams and Beam Predictor

TL;DR

This paper introduces a joint optimization framework for probe beam sensing and prediction in mmWave communications, reducing overhead and delay through deep learning and manifold-constrained beam design.

Contribution

It proposes a novel joint optimization of data- and model-driven probe beams and a cascaded predictor within manifold constraints, enhancing beam prediction accuracy.

Findings

Significant reduction in beam training overhead.

Improved beam prediction accuracy with neural network-based sensing.

Effective mitigation of quantization errors through phase noise addition.

Abstract

Hierarchical search in millimeter-wave (mmWave) communications incurs significant beam training overhead and delay, especially in a dynamic environment. Deep learning-enabled beam prediction is promising to significantly mitigate the overhead and delay, efficiently utilizing the site-specific channel prior. In this work, we propose to jointly optimize a data- and model-driven probe beam module and a cascaded data-driven beam predictor, with limitations in that the probe and communicate beams are restricted within the manifold space of uniform planer array and quantization of the phase modulator. First, The probe beam module senses the mmWave channel with a complex-valued neural network and outputs the counterpart RSRPs of probe beams. Second, the beam predictor estimates the RSRPs in the entire beamspace to minimize the prediction cross entropy and selects the optimal beam with the maximum RSRP value for data transmission. Additionally, we propose to add noise to the phase variables in the probe beam module, against quantization error. Simulation results show the effectiveness of our proposed scheme.