In this paper, we present a novel clustering-based resource allocation framework for downlink transmission in ultra-dense small cell networks. Specifically, we first model a combinatorial optimisation problem that jointly considers subchannel and power allocation and user traffic demand in terms of a large-scale network scenario. Unfortunately, the huge communication overhead and computational complexity make it challenging for traditional centralised/distributed solutions. To address this issue, we propose an interference-separation clustering-based scheme to divide the massive small cells into smaller groups with different priorities, which reduces the network scale. Different from the existing cluster construction scheme, the proposed clustering method effectively avoids the inter-cluster interference through coordination. Then, for a given cluster configuration, we formulate the distributed resource allocation problem as a local interaction game where the utility of each player comprises not only its own profits but also the interests of neighbours. We prove the existence of Nash equilibrium for the formulated game and design a hierarchical learning algorithm to achieve the Nash equilibrium, which only needs local information exchange. Finally, simulation results validate that the proposed solution outperforms some other existing approaches and is more suitable for large-scale networks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.