Machine Learning-based Urban Canyon Path Loss Prediction using 28 GHz Manhattan Measurements

TL;DR

This paper presents a machine learning model for predicting urban canyon path loss at 28 GHz using extensive Manhattan measurements, LiDAR data, and advanced feature extraction to improve accuracy and generalizability over traditional models.

Contribution

It introduces a novel ML-based urban canyon path loss prediction method that leverages LiDAR and building data with a street-by-street training approach for better accuracy.

Findings

Prediction RMSE of 4.8 dB with the proposed model

Outperforms 3GPP LOS and slope-intercept models

Using four key clutter features yields RMSE of 5.5 dB

Abstract

Large bandwidth at mm-wave is crucial for 5G and beyond but the high path loss (PL) requires highly accurate PL prediction for network planning and optimization. Statistical models with slope-intercept fit fall short in capturing large variations seen in urban canyons, whereas ray-tracing, capable of characterizing site-specific features, faces challenges in describing foliage and street clutter and associated reflection/diffraction ray calculation. Machine learning (ML) is promising but faces three key challenges in PL prediction: 1) insufficient measurement data; 2) lack of extrapolation to new streets; 3) overwhelmingly complex features/models. We propose an ML-based urban canyon PL prediction model based on extensive 28 GHz measurements from Manhattan where street clutters are modeled via a LiDAR point cloud dataset and buildings by a mesh-grid building dataset. We extract expert knowledge-driven street clutter features from the point cloud and aggressively compress 3D-building information using convolutional-autoencoder. Using a new street-by-street training and testing procedure to improve generalizability, the proposed model using both clutter and building features achieves a prediction error (RMSE) of $4.8 \pm 1.1$ dB compared to $10.6 \pm 4.4$ dB and $6.5 \pm 2.0$ dB for 3GPP LOS and slope-intercept prediction, respectively, where the standard deviation indicates street-by-street variation. By only using four most influential clutter features, RMSE of $5.5\pm 1.1$ dB is achieved.