Gaussian mixture model based radio environment mapping for an underlay Device‐to‐Device network

Abstract

AbstractEfficient management of the scant radio resources in densely deployed Device‐to‐Device (D2D) and IoT networks in 5G+ and 6G wireless era would require continuous and reliable information feedback regarding the actual on‐ground resource utilization. Toward that goal, radio environment maps (REM) are becoming increasingly important as they provide critical information relevant for network management. REM essentially entails the estimation of the radio environment at unsampled locations using the values measured by a few dedicated REM sensors by interpolation. Hence, the accuracy of REM is dependent upon two major factors (1) the sensor deployment and (2) the interpolation scheme. So far, the ordinary Kriging (OK) with randomly deployed sensors is the most prevalent method of REM creation. However, the underlying assumption in OK is that the radio environment conforms to a Gaussian spatial random field (GSRF). In reality, the spatial random field generated by a D2D network displays non‐Gaussian characteristics. Hence, a variational Bayesian based Gaussian mixture model enabled Kriging (VK) method has been proposed in this work which achieves better interpolation accuracy than OK with a lower run‐time computational complexity. A comparison of various sensor deployment schemes on the basis of REM accuracy in fading channel conditions has also been conducted. Additionally, a spatial‐correlation based method has been proposed to estimate the minimum number of required REM sensors to ensure reliable REM performance. The simulation results indicate a superiority of hexagonal deployment of sensors over other schemes and establish VK as a more accurate interpolation algorithm than OK.