An artificial intelligence‐based spectrum sensing methodology for LoRa and cognitive radio networks

Abstract

SummaryThe artificial intelligence‐based spectrum sensing approach is extremely important in terms of effective bandwidth utilization for low power wide area networks (LPWANs) based on cognitive radio networks (CRNs). Most studies perform spectrum detection with CRNs using optimization or deep neural network methods. However, optimization‐based spectrum detection approaches based on current LPWANs are scarce. For this purpose, in this study, a hybrid optimization methodology integrated with CRNs is proposed for LoRa, which is one of the most compatible LPWAN technologies in the Internet of Things (IoTs) recently. In the particle swarm optimization (PSO) part of this hybrid methodology, agent users are created so that secondary users (SUs) could use the licensed band of primary users (PUs) in cognitive radio. On the genetic algorithm side, LoRa error rates are minimized in order to further improve the performance of the proposed method. In this way, effective spectrum sensing is performed in the LoRa network. Various LoRa‐CRN experiments have been carried out in the simulation environment, and the probability of detection and false alarm performances have been compared with both theoretical and proposed approaches in terms of quality estimation parameters. It is clear from the results that the proposed methods give successful results for the LoRa‐CRNs.