Hierarchical Federated Learning over HetNets enabled by Wireless Energy Transfer

Training centralized machine learning (ML) models becomes infeasible in wireless networks due to the increasing number of internet of things (IoT) and mobile devices and the prevalence of the learning algorithms to adapt tasks in dynamic situations with heterogeneous networks (HetNets) and battery limited devices. Hierarchical federated learning (HFL) has been proposed as a promising learning that can preserve the data privacy of the wireless devices, tackle the communication bottlenecks in wireless networks, and improve the energy effi-ciency. We propose a novel energy-efficient HFL framework for HetNets with massive multiple-input multiple-output (MIMO) wireless backhaul enabled by wireless energy transfer (WET). We formulate a joint energy management and device association optimization problem in HFL over HetNets subject to maximal divergence constraints. Next, an optimal solution is developed, but with high complexity. To reduce the complexity, a heuristic algorithm for HFL over HetNets with energy, channel quality, and accuracy constraints, is developed in order to minimize the grid energy consumption cost and preserve the value of loss function, which captures the HFL performance. Simulation results show the efficiency of the proposed resource management approach in the HFL context in terms of grid power consumption cost and training loss.