Novel method for multi-user collaborative spectral decision in decentralized cognitive radio networks

Abstract

Cognitive radio networks positively impact the performance of wireless communications and have proven to be an excellent alternative for efficient and effective use of the radio spectrum. However, few proposals collaboratively work on decision-making in decentralized cognitive radio networks. The present work refers to a novel method and device that reduces the rate of channel changes during secondary user communications in decentralized cognitive radio networks through a collaborative spectral decision between several secondary users while allowing multiple secondary users access to the network. This proposal consists of a multi-user unit that regulates the access of multiple secondary users (SUs) to the spectrum, a priority unit that guarantees timely access to the SUs according to their level of importance, and a prediction unit that forecasts the arrival time of the primary user (PU). This multichannel unit regulates the assignment of multiple spectral opportunities to the SU according to the type of application it is using and a unit of deep learning that determines which spectral opportunity(s) are most suitable for each SU and spectral allocation. The results obtained allow us to satisfactorily validate the proposal developed and corroborate the importance of collaborative work in decision-making to select spectral opportunities.