Wireless Energy Harvesting (WEH) and Spectrum Sharing in Cognitive Radio Networks

Abstract

  Cognitive Radio Networks (CRNs) have the potential to improve energy efficiency and spectrum usage through the integration of Wireless Energy Harvesting (WEH) with spectrum sharing. According to the findings of this research, a unique Deep Reinforcement Learning (DRL) approach has been developed with the intention of increasing the availability of spectrum and making it possible for secondary users to effectively harvest energy. By dynamically adjusting spectrum sharing decisions in accordance with the energy availability of secondary users, the DRL model enhances network performance. This model places an emphasis on the essential aspect of "harvested energy." The findings of the simulation indicate that the DRL-based technique that was proposed greatly enhances the efficacy and throughput of CRNs, which highlights the potential of this approach for conducting wireless communication over extended periods of time.