Fast Radio Propagation Prediction with Deep Learning
In this chapter, we consider the problem of estimating radio maps for wireless communication systems, namely, computing the propagation pathloss from a point x (transmitter location) to any point y on a planar domain. For applications such as user-cell site association and device-to-device link scheduling, an accurate knowledge of the pathloss function for all pairs of transmitter–receiver locations is very important. In realistic propagation environments characterized by the presence of buildings, street canyons, and objects at different heights, commonly used radial-symmetric functions yield very misleading results. On the other hand, ray-tracing and related methods capture more accurately the shadowing, reflection, and diffraction patterns but require high computational power. The goal in this chapter is to show that properly designed and trained deep neural networks are able to learn how to estimate the pathloss function, given an urban environment, with comparable accuracy to ray-tracing methods, but orders of magnitude faster. The radio map estimation problem is seen as an image-to-image task, in which the map of the city and additional domain information are transformed to the corresponding radio map. Hence, we base the estimation method on UNets, which are a ubiquitous class of convolution networks in imaging tasks.
