Intelligent Secondary LTE Spectrum Sharing in High Capacity Cognitive Cellular Systems

This paper investigates the distributed Q-learning approach to secondary LTE spectrum sharing, its autonomously emerging spectrum usage patterns, and their impact on the primary and secondary user quality of service (QoS). Large scale simulations of a stadium temporary event scenario show that it is capable of servicing a dramatic 51-fold increase in offered traffic, but with no need for additional spectrum and with no perceived degradation in the primary user QoS.