Detection of Spectral Resources in Cognitive Radios Using Reinforcement Learning

Available spectrum for wireless communications is a limited resource which gains importance with the increasing demand for mobile communication services with high data rates. Measurements show that assigned frequency bands (FBs) are not used efficiently. One approach for increasing the efficiency in spectrum use is the concept of overlay systems, which can be seen as an enabling technology for cognitive radio and dynamic spectrum access by providing frequency agility. In this paper, we propose an approach for the detection of spectral resources based on reinforcement learning, allowing the cognitive radio to select the FBs with the most available resources.