Multi-UAV-Assisted Federated Learning for Energy-Aware Distributed Edge Training

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) has largely extended the border and capacity of artificial intelligence of things (AIoT) by providing a key element for enabling flexible distributed data inputs, computing capacity, and high mobility. To enhance data privacy for AIoT applications, federated learning (FL) is becoming a potential solution to perform training tasks locally on distributed IoT devices. However, with the limited onboard resources and battery capacity of each UAV node, optimization is required to achieve a large-scale and high-precision FL scheme. In this work, an optimized multi-UAV-assisted FL framework is designed, where regular IoT devices are in charge of performing training tasks, and multiple UAVs are leveraged to execute local and global aggregation tasks. An online resource allocation (ORA) algorithm is proposed to minimize the training latency by jointly deciding the selection decisions of clients and a global aggregation server. By leveraging the Lyapunov optimization technique, virtual energy queues are studied to depict the energy deficit. With the help of the actor-critic learning framework, a deep reinforcement learning (DRL) scheme is designed to improve per-round training performance. A deep neural network (DNN)-based actor module is designed to derive client selection decisions, and a critic module is proposed through a conventional optimization method to evaluate the obtained selection decisions. Moreover, a greedy scheme is developed to find the optimal global aggregation server. Finally, extensive simulation results demonstrate that the proposed ORA algorithm can achieve optimal training latency and energy consumption under various system settings.

I. Introduction

Recently, artificial intelligence (AI) has been introduced into the Internet of Things (IoT) frontier to seek efficient solutions, which paves the way for the burgeoning Artificial Intelligence of Things (AIoT) [1], [2], [3]. Especially, deep learning has been proven to be a promising enabler for efficient information retrieval from a tremendous amount of data, in the fields of computer vision and pattern recognition. The great explosion of IoT devices brings the exponential growth of data, where the number of IoT devices will reach 41.6 billion by 2025. To achieve deep insights from the data gathered by IoT devices, edge intelligence has emerged as an enabler to enhance AIoT system performance by providing resources at the edge of the network. However, the limitations of network resources and the concern of privacy leakage make the centralized edge training framework unsuitable for future communication networks [4]. To address the aforementioned issues, federated learning (FL) is becoming a potential approach dedicated to preserving privacy by distributing training tasks among distributed IoT devices [5], [6], [7]. Each IoT device serves as a client to train a shared deep neural network (DNN) model by local data and uploads the computed updates to a server for aggregation.