Machine learning aided cognitive RAT selection for 5G heterogeneous networks

Abstract

The starring role of the Heterogeneous Networks (HetNet) strategy as the key Radio Access Network (RAN) architecture for future 5G networks poses serious challenges to the current user association (cell selection) mechanisms used in cellular networks. The max-SINR algorithm, although historically effective for performing this function, is inefficient at best and obsolete at worst in 5G HetNets. The foreseen embarrassment of riches and diversified propagation characteristics of network attachment points spanning multiple Radio Access Technologies (RAT) requires novel and creative context-aware system designs that optimize the association and routing decisions in the context of single-RAT and multi-RAT connections, respectively. This paper proposes a framework under these guidelines that relies on Machine Learning techniques at the terminal device level for Cognitive RAT Selection and presents simulation results to suppport it.