Interpretable AI-based Large-scale 3D Pathloss Prediction Model for enabling Emerging Self-Driving Networks

TL;DR

This paper introduces an interpretable machine learning model for large-scale 3D pathloss prediction in wireless networks, significantly improving accuracy and speed over traditional models and ray-tracing, with insights for practical network tuning.

Contribution

The study presents a novel ML-based pathloss prediction model using LightGBM, demonstrating superior accuracy, efficiency, and interpretability through SHAP analysis compared to existing methods.

Findings

LightGBM outperforms other ML algorithms in accuracy and speed.

The model achieves 65% higher accuracy than empirical models.

Prediction time is reduced by 13 times compared to ray-tracing.

Abstract

In modern wireless communication systems, radio propagation modeling to estimate pathloss has always been a fundamental task in system design and optimization. The state-of-the-art empirical propagation models are based on measurements in specific environments and limited in their ability to capture idiosyncrasies of various propagation environments. To cope with this problem, ray-tracing based solutions are used in commercial planning tools, but they tend to be extremely time-consuming and expensive. We propose a Machine Learning (ML)-based model that leverages novel key predictors for estimating pathloss. By quantitatively evaluating the ability of various ML algorithms in terms of predictive, generalization and computational performance, our results show that Light Gradient Boosting Machine (LightGBM) algorithm overall outperforms others, even with sparse training data, by providing a 65% increase in prediction accuracy as compared to empirical models and 13x decrease in prediction time as compared to ray-tracing. To address the interpretability challenge that thwarts the adoption of most ML-based models, we perform extensive secondary analysis using SHapley Additive exPlanations (SHAP) method, yielding many practically useful insights that can be leveraged for intelligently tuning the network configuration, selective enrichment of training data in real networks and for building lighter ML-based propagation model to enable low-latency use-cases.