Decentralized Sensor Selection for Cooperative Spectrum Sensing Based on Unsupervised Learning

In this paper, decentralized cooperative spectrum sensing in cognitive radio networks is studied based on the recent advances in unsupervised learning. To balance a tradeoff between the sensing reliability and the cooperation overhead (e. g., energy, delay, and signaling, etc.), a distributed clustering algorithm, without any central coordinator, is introduced for inducing the sensors with the best detection performance to join together and take charge of cooperative spectrum sensing. Numerical results show that the proposed scheme can obtain detection performance comparable to that of optimal soft combination scheme with reduced cooperation overhead. Moreover, the proposed scheme does not require any priori knowledge of spectrum sensors' received signal-to-noise-ratios (SNRs) or locations.