Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networks

Abstract

Radio propagation modeling and prediction is fundamental for modern cellular network planning and optimization. Conventional radio propagation models fall into two categories. Empirical models, based on coarse statistics, are simple and computationally efficient, but are inaccurate due to oversimplification. Deterministic models, such as ray tracing based on physical laws of wave propagation, are more accurate and site specific. But they have higher computational complexity and are inflexible to utilize site information other than traditional global information system (GIS) maps.In this article we present a novel method to model radio propagation using deep convolutional neural networks and report significantly improved performance compared to conventional models. We also lay down the framework for data-driven modeling of radio propagation and enable future research to utilize rich and unconventional information of the site, e.g. satellite photos, to provide more accurate and flexible models.

Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach

“…The need for accurate predictions of propagation path loss has driven the research among various machine learning algorithms [1][2][3][4][5][6][7][8][9]. Substantial efforts have been made in order to optimally define their internal configuration [10][11][12], in an attempt to achieve the best results possible.…”

“…While the classical machine learning models that depend on tabular data have already proved their value, a new category of models, based on deep learning and using images as their inputs, has emerged [6][7][8][9]18].…”

“…CNNs have the ability to perform predictions, based on images of the area's as map [6][7][8][9]. The same holds true when these networks receive appropriate pseudoimages at their inputs.…”

“…The second category of models, which delivers its predictions based on images, is generally being referred to as Deep Learning. CNNs [6][7][8][9] are used in order to extract information from images and perform predictions.…”

An Expedient, Generalizable and Realistic Data-Driven Indoor Propagation Model

“…In particular, artificial neural networks (ANNs) have been widely used in an effort to expedite [19] or even replace ray tracing simulators [20]. The preponderance of past research concentrates on urban propagation scenarios [20]- [23], however as has been mentioned, indoor propagation modeling is of high significance in the deployment of 5G networks. Currently, most of the existing approaches on indoor propagation modeling are confined to the use of simple multilayer perceptrons (MLPs) [24] to determine the radio channel characteristics [19], [25].…”