An improved genetic algorithm approach to spectrum sensing for long range based cognitive radio networks

Abstract

AbstractBy designing cognitive radio networks (CRNs) for low power wide area networks (LPWANs), adaptive spectrum sensing plays an important role in using frequency bands effectively. With spectrum sensing, existing spectrum holes are filled by enabling secondary users to use the licensed band that primary users do not use. Many researchers have proposed various optimization or artificial intelligence techniques in CRNs for spectrum sensing. However, there is hardly any adaptive spectrum sensing method integrated into the LoRa communication standard, which is a very popular LPWAN technology. For this purpose, an adaptive optimization based spectrum sensing methodology with an improved genetic algorithm is proposed in this study. Depending on this methodology, two fitness functions adapted to the LoRa‐based network are defined. Thanks to these functions, the movement of individuals in the network population is provided. In parallel, received signal strength values of optimum LoRa nodes were determined by genetic coding, and bands to be used by SUs instead of PUs were discovered considering minimum bit errors. To verify the success of the proposed method, various simulation experiments were carried out. The performance results strikingly show that the proposed method is quite successful for LoRa‐CRNs. For example, the proposed method significantly improved the bit error rate performance, and reduced the number of faulty transmissions caused by packet collisions. It also reduced the packet error rate by more than 8% per minute in a 200‐node network.