A Radio Environment Maps Estimation Algorithm based on the Pixel Regression Framework for Underlay Cognitive Radio Networks Using Incomplete Training Data

Abstract

In the underlay cognitive radio networks, the radio environment maps (REMs) estimation is the main challenge in sensing the idle wireless spectrum resources. Traditional deep learning-based algorithms estimate the REMs on the basis of the high-quality, large-scale complete training images. However, collecting the complete radio environment images is time-consuming and requires a numerous number of power spectrum sensing nodes. For this reason, we propose a generative adversarial networks-based pixel regression framework (PRF) for underlay cognitive radio networks. The PRF algorithm relaxes the requirement of the complete training images, and estimates the radio environment maps only on the basis of the incomplete REMs images, which are easier to be collected. First, we transform the radio environment maps estimation task into a pixel regression task through the color mapping progress. Then, to extract helpful information from the incomplete training data, we design a feature enhancing module for the PRF algorithm, which intelligently learns and emphasizes the important features from the training images. Finally, we use the trained pixel regression framework to reconstruct the radio environment maps in the target area. The proposed algorithm learns accurate radio environment characteristics from the incomplete training data rather than making direct biased or imprecise radio propagation assumptions as in the traditional methods. Thus, the PRF algorithm has a better REMs reconstruction performance than the traditional methods, as verified by simulations.Sensors 2020, 20, 2245 2 of 17 use the licensed band if the interference does not exceed the thresholds of the primary users because of the power attenuation in the wireless radio propagation path [8]. The above radio resources allocation scheme improves the spectrum efficiency by utilizing the wireless "white space", which is about the idle licensed spectrum resource in the space and frequency domains. The underlay CRN has strict requirements of the working power of the SUs, which can significantly improve the utilization of the radio resources based on the efficient and intelligent spectrum management.In the underlay cognitive radio network, we adopt the radio environment maps (REMs) to display the primary users' power spectrum (PS) in the CRN area. It is a visible map of the wireless environment, which adds the PS information into the spatial map. Based on the estimation of the REMs, we can handle the conflict between the SUs and PUs and maximize the utilization of the spectrum resources in a particular CRN region.Estimating and utilizing the radio environment maps is extraordinarily helpful in wide-area CRN [9]. To reduce the interference to PUs, the SUs intelligently change their transmitting power on the basis of the REMs, allowing the remote users to dynamically utilize the idle radio resources [10,11].As shown in Figure 1, for estimating the radio environment maps, the general setting includes several transmitting PUs and receiving SUs. We suppose that they ...

DeepREM: Deep-Learning-Based Radio Environment Map Estimation From Sparse Measurements

“…Since real measurements obtained either with drive tests or other sources are typically sparsely distributed in the area of interest [31], we simulate these incomplete maps according to the following process. Let (i, j) be the spatial coordinates of the complete map m and m the incomplete map.…”