Energy-Efficient Federated Learning for Wireless Computing Power Networks

Abstract

In the 6G era, the proliferation of data poses unprecedented challenges on the current computing networks. The collaboration among cloud computing, edge computing and networking is imperative to process such massive data, eventually realizing ubiquitous computing and intelligence. In this paper, we propose a Wireless Computing Power Networks (WCPN) by orchestrating the computing and networking resources of heterogeneous nodes towards specific computing tasks. To enable collaborative intelligence in WCPN, we design an energy-efficient federated learning model, which minimizies the sum energy consumption of all nodes by the joint optimization of the computing capability and the collaborative learning strategy. Based on the solution of the optimization problem, the neural network depth of computing nodes and the collaboration frequency among nodes are adjustable according to specific computing task requirements and resource constraints. Numerical results show that the proposed scheme outperforms the existing work in terms of convergence rate, learning accuracy, and energy saving.