Cooperative spectrum sensing using Q-learning with experimental validation

Spectrum sensing detects the availability of the radio frequency spectrum and it is essential to cognitive radio. Cooperative spectrum sensing conducted among multiple secondary users has the potentials for solving the hidden terminal problem and achieving a better performance. In this paper, an approach for cooperative spectrum sensing based on Q-learning is proposed. Real-world Wi-Fi signals measured from four different locations are employed to evaluate the performance of the proposed approach. Experimental result shows the performance of the proposed approach is better than that of the popular M-out-of-N rule. The proposed approach is effective. This work is a part of the efforts toward building a cognitive radio network testbed.