Model-Free Radio Map Estimation in Massive MIMO Systems via Semi-Parametric Gaussian Regression

Nicolò Dal Fabbro, Michele Rossi, Gianluigi Pillonetto, Luca Schenato, Giuseppe Piro

Abstract: Accurate radio maps will be very much needed to provide environmental awareness and effectively manage future wireless networks. Most of the research so far has focused on developing power mapping algorithms for single and omnidirectional antenna systems. In this letter, we investigate the construction of crowdsourcing-based radio maps for 5G cellular systems with massive directional antenna arrays (spatial multiplexing), proposing an original technique based on semi-parametric Gaussian regression. The proposed method is <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">model-free</i> and provides highly accurate estimates of the radio maps, outperforming fully parametric and non-parametric solutions.