PMNet: Robust Pathloss Map Prediction via Supervised Learning

TL;DR

PMNet is a neural network-based method for predicting wireless pathloss maps that reduces computational costs and outperforms existing models by leveraging supervised learning and computer vision techniques.

Contribution

This paper introduces PMNet, a novel supervised learning neural network architecture for pathloss prediction that requires less data and computational effort than traditional ray tracing methods.

Findings

PMNet achieves higher accuracy than UNet and RadioUNet.

PMNet generalizes well with limited training data.

PMNet trained on smaller datasets outperforms larger dataset baselines.

Abstract

Pathloss prediction is an essential component of wireless network planning. While ray tracing based methods have been successfully used for many years, they require significant computational effort that may become prohibitive with the increased network densification and/or use of higher frequencies in 5G/B5G (beyond 5G) systems. In this paper, we propose and evaluate a data-driven and model-free pathloss prediction method, dubbed PMNet. This method uses a supervised learning approach: training a neural network (NN) with a limited amount of ray tracing (or channel measurement) data and map data and then predicting the pathloss over location with no ray tracing data with a high level of accuracy. Our proposed pathloss map prediction-oriented NN architecture, which is empowered by state-of-the-art computer vision techniques, outperforms other architectures that have been previously proposed (e.g., UNet, RadioUNet) in terms of accuracy while showing generalization capability. Moreover, PMNet trained on a 4-fold smaller dataset surpasses the other baselines (trained on a 4-fold larger dataset), corroborating the potential of PMNet.