Joint AAV Deployment and Edge Association for Energy-Efficient Federated Learning

Recently, federated learning (FL) has become a promising distributed learning paradigm that caters to the recent trend of pushing intelligence from the cloud to the edge. Nevertheless, communication bottlenecks and device dropout can lead to inefficient FL in the large network scale, where massive devices cannot be accessed with severely limited network resources. Inspired by the autonomous aerial vehicle (AAV)-assisted mobile edge computing (MEC), we propose the multi-AAV assisted FL design to provide the intermediate model aggregation in the sky. Specifically, we study the problem of joint UAV dePloyment and edge aSsociation (UPS) to minimize the overall energy consumption, which concerns UAV deployment,…

• NN
  National Natural Science Foundation of China

  Awards: 62072303, 62372456, No. 62372456