Distributed learning approach for channel selection in Cognitive Radio Networks

In this paper, we address the channel selection problem with switching cost and propose a distributed learning approach that minimizes the sum regret while ensuring quick convergence to an optimal solution and logarithmic regret. Our algorithm is adaptive in the sense that it adapts to the changing idle status of channels and achieves logarithmic regret even in a dynamic environment. The experimental result shows that our algorithm outperforms the existing algorithm in terms of regret, scalability and channel switching cost.