Enhancing Cognitive Radio dynamic spectrum sensing through adaptive learning

Cognitive Radio (CR) networks present a difficult set of challenges due to the fluctuating nature of the available spectrum and wide ranging number of applications, each having different Quality of Service (QoS) requirements. This paper studies the key enabling technologies of Cognitive Radio and makes contributions in two key areas: sensing and learning. We shall first present the software testbed which is developed to implement the Cognitive Radio spectrum sensing system. Next, we derive the mathematical relationship between varying parameters and the QoS and test it on our system to verify the overall performance. Novel learning techniques which determine the statistics of primary user (PU) channel usage over time are proposed to enhance the cognitive radio's dynamic spectrum sensing ability. Using our testbed, we shall demonstrate the feasibility of the innovative adaptive learning algorithms and their ability to increase spectrum sensing efficiency and improve performance over time without feedback from the receiver. We will then proceed to the domain where there are multiple non-cooperative cognitive users (secondary users) selfishly applying the learning algorithms to increase their data rate in channels with varying primary user activity. Finally we conclude with discussions about our results and future work.