Distributed Q-learning based dynamic spectrum access in high capacity density cognitive cellular systems using secondary LTE spectrum sharing

In this paper a distributed Q-learning based dynamic spectrum access (DSA) algorithm is applied to a cognitive cellular system designed for providing ultra high capacity density with only secondary access to an LTE channel. Large scale simulations of a stadium temporary event scenario show that the distributed Q-learning based DSA scheme provides robust quality of service (QoS) and extremely high system throughput densities to the users of the stadium network, whilst successfully coexisting with a primary network of macro eNodeBs on the same LTE channel. It is also shown that incorporating spectrum awareness or spectrum sensing based admission control into the DSA algorithm in this scenario does not improve its performance. Therefore, distributed Q-learning based DSA is a viable and easily implementable solution for facilitating secondary LTE spectrum sharing in high capacity density cognitive cellular systems.