Learning-Aided Sensing Scheduling for Wide-Band Cognitive Radios

Spectrum sensing scheduling policies are proposed to find spectrum opportunities for wide-band cognitive radios by taking into account realistic reconfiguration energy consumptions and time delays. The first policy relies on the RF environment Markov properties. Thus, it may become computationally demanding. The second sub-band selection policy based on Q-learning is proposed to circumvent this. Performance of the two policies are compared and discussed against a performance upper-bound of the optimal solution to the corresponding partially observable Markov decision process formulation. The suitability of the Q-learning technique is validated by showing that it achieves good performance in simulation.