UAV Swarm Collaborative Transmission Optimization for Machine Learning Tasks
Liangchen Chao, Bo Zhang, Hengpeng Guo, Fangheng Ji, Junfeng Li · 2024
Recent developments in artificial intelligence technologies have seen an increasing volume of real-time data, collected by unmanned aerial vehicle (UAV), and processed by machine learning (ML) techniques instead of human labor. Traditional transmission techniques aiming at low loss rates are hence rendered ineffective for ML. In this paper, we investigate a collaborative transmission optimization method among a group of UAVs, with the goal of maximizing the efficiency of server-side ML tasks. Towards this end, we propose a novel network-coding enabled multi-agent deep reinforcement learning approach named DC-MAPPO in the UAV Ad Hoc network with limited resources. Our method deploys random linear network coding for source packet coding, with an improved multi-agent proximal policy optimization algorithm combining the dual-clip method for broadcasting strategy optimization. We adopt a handwriting recognition algorithm based on the MNIST dataset to verify the effectiveness of DC-MAPPO. Simulation results demonstrate that DC-MAPPO outperforms baseline schemes in terms of rewards, rate of convergence, and recognition efficiency of ML algorithms.