Uncertainty Estimation for Path Loss and Radio Metric Models

TL;DR

This paper applies Conformal Prediction to radio metric models to provide reliable uncertainty estimates, demonstrating robustness and generalization across different cities and datasets.

Contribution

It introduces the use of Conformal Predictive Systems for uncertainty estimation in radio models, showing effective generalization and sample difficulty identification.

Findings

CPS models achieve 95% confidence intervals with high coverage.

Models trained on Toronto data generalize well to Vancouver and Montreal.

Difficulty estimators reduce RMSE by identifying challenging samples.

Abstract

This research leverages Conformal Prediction (CP) in the form of Conformal Predictive Systems (CPS) to accurately estimate uncertainty in a suite of machine learning (ML)-based radio metric models [1] as well as in a 2-D map-based ML path loss model [2]. Utilizing diverse difficulty estimators, we construct 95% confidence prediction intervals (PIs) that are statistically robust. Our experiments demonstrate that CPS models, trained on Toronto datasets, generalize effectively to other cities such as Vancouver and Montreal, maintaining high coverage and reliability. Furthermore, the employed difficulty estimators identify challenging samples, leading to measurable reductions in RMSE as dataset difficulty decreases. These findings highlight the effectiveness of scalable and reliable uncertainty estimation through CPS in wireless network modeling, offering important potential insights for network planning, operations, and spectrum management.