PMNet: Robust Pathloss Map Prediction via Supervised Learning

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.

[1]  R. Valenzuela,et al.  Machine Learning-Based Urban Canyon Path Loss Prediction Using 28 GHz Manhattan Measurements , 2022, IEEE Transactions on Antennas and Propagation.

[2]  Daniel Romero,et al.  Radio Map Estimation: A data-driven approach to spectrum cartography , 2022, IEEE Signal Processing Magazine.

[3]  Sotirios K. Goudos,et al.  Enhancing Machine Learning Models for Path Loss Prediction Using Image Texture Techniques , 2021, IEEE Antennas and Wireless Propagation Letters.

[4]  Giuseppe Caire,et al.  RadioUNet: Fast Radio Map Estimation With Convolutional Neural Networks , 2019, IEEE Transactions on Wireless Communications.

[5]  Takayuki Okatani,et al.  Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries , 2018, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV).

[6]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Dongsoo Han,et al.  Voronoi Tessellation Based Interpolation Method for Wi-Fi Radio Map Construction , 2012, IEEE Communications Letters.

[12]  E. Vitucci,et al.  Measurement and Modelling of Scattering From Buildings , 2007, IEEE Transactions on Antennas and Propagation.

[13]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[14]  Reinaldo A. Valenzuela,et al.  Radio propagation measurements and prediction using three-dimensional ray tracing in urban environments at 908 MHz and 1.9 GHz , 1999 .

[15]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[16]  B. Gunturk,et al.  PL-GAN: Path Loss Prediction Using Generative Adversarial Networks , 2022, IEEE Access.

[17]  Vishnu V. Ratnam,et al.  FadeNet: Deep Learning-Based mm-Wave Large-Scale Channel Fading Prediction and its Applications , 2021, IEEE Access.

[18]  Jae-Han Lee,et al.  Multi-loss Rebalancing Algorithm for Monocular Depth Estimation , 2020, ECCV.

[19]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[20]  F. Landstorfer,et al.  Dominant Path Prediction Model for Urban Scenarios , 2005 .