Distributed User Association in Energy Harvesting Dense Small Cell Networks: A Mean-Field Multi-Armed Bandit Approach

The emerging ultra-dense small cell networks (UD-SCNs) will need to combat a variety of challenges. On the one hand, massive number of devices sharing the limited wireless resources renders centralized control mechanisms infeasible due to the excessive cost of information acquisition and computation. On the other hand, to reduce the energy consumption from fixed power grid and/or battery, network entities (e.g., small cell base stations and user devices) may need to rely on the energy harvested from the ambient environment (e.g., from environmental sources). However, opportunistic energy harvesting introduces uncertainty in the network operation. In this paper, we study the distributed user association problem for energy harvesting UD-SCNs. After reviewing the state-of-the-art research, we outline the major challenges that arise in the presence of energy harvesting due to the uncertainty (e.g., limited knowledge on energy harvesting process or channel profile) as well as limited computational capacities. Finally, we propose an approach based on the mean-field multi-armed bandit games to solve the uplink user association problem for energy harvesting devices in a UD-SCN in the presence of uncertainty.