Intelligent Dynamic Spectrum Access in Cellular Systems with Asymmetric Topologies and Non-Uniform Traffic Loads

This paper assesses the robustness of the distributed reinforcement learning (RL) approach to dynamic spectrum access (DSA) in cellular systems with asymmetric topologies and non-uniform offered traffic distributions. Large scale simulations of a stadium small cell LTE network, employing a distributed Q-learning based DSA scheme, show that such asymmetries in the network environment cause no degradation of the QoS provided to any part of the network.