Low-Complexity Learning for Dynamic Spectrum Access in Multi-User Multi-Channel Networks

In Cognitive Radio Networks (CRNs), dynamic spectrum access allows (unlicensed) users to identify and access unused channels opportunistically, thus improves spectrum utility. In this paper, we address the user-channel allocation problem in multi-user multi-channel CRNs without a prior knowledge of channel statistics. A reward of a channel is stochastic with unknown distribution, and statistically different for each user. Each user either explores a channel to learn the channel statistics, or exploits the channel with the highest expected reward based on information collected so far. Further, a channel should be accessed exclusively by one user at a time due to a collision. Using multi-armed bandit framework, we develop a provably efficient solution whose computational complexity is linear to the number of users and channels.