Learning-Based Spectrum Sensing Time Optimization in Cognitive Radio Systems

Powerful spectrum sensing schemes enable cognitive radios (CRs) to find transmission opportunities in spectral resources allocated exclusively to primary users. In this paper, the problem of maximizing the average throughput of a cognitive radio system through optimizing its spectrum sensing time is investigated, and a systematic neural network-based optimization approach is proposed which avoids challenges associated with the conventional analytical solutions. The proposed method exploits a novel learning and optimization cycle to enable an effective cooperation between two kinds of well-known artificial neural networks and finds the optimum value of the channel sensing time without any prior knowledge or assumption about the wireless environment. The structure and algorithm of the proposed sensing time optimization scheme are discussed in detail, and a set of illustrative numerical results is presented to validate its performance.