Layered Learning Radio Resource Management for Energy Harvesting Small Base Stations

Dense deployment of small base stations (SBSs) will play a crucial role in 5G cellular networks for satisfying the expected huge traffic demand. Dynamic ON/OFF switching of SBSs and the use of renewable energies have recently attracted increasing attention to limit the energy consumption of such a network. In this paper, we present a Layered Learning solution for the radio resource management of dense cellular networks with SBSs powered solely by renewable energy. In the first layer, reinforcement learning agents locally select switch ON/OFF policies of the SBSs according to the energy income and the traffic demand. The second layer relies on an Artificial Neural Network that estimates the network load conditions to implement a centralized controller enforcing local agent decisions. Simulation results prove that the proposed layered framework outperforms both a greedy and a completely distributed solution both in terms of throughput and energy efficiency.