AUTHOR=Lai Qijie , Xie Rongchang , Yang Zhifei , Wu Guibin , Hong Zechao , Yang Chao 

TITLE=Efficient multiple unmanned aerial vehicle-assisted data collection strategy in power infrastructure construction

JOURNAL=Frontiers in Communications and Networks

VOLUME=Volume 5 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/communications-and-networks/articles/10.3389/frcmn.2024.1390909

DOI=10.3389/frcmn.2024.1390909

ISSN=2673-530X

ABSTRACT=Efficient data collection and sharing perform the crucial part in the power infrastructure construction.However, in the outdoor remote area, the data collection efficiency is reduced for the sparse distribution of base stations (BS). Unmanned Aerial Vehicles (UAVs) can perform as the flying BS for the mobility and the line-of-sight transmission features. In this paper, we propose a multiple temporary UAV-assisted data collection system in power infrastructure scenario, multiple temporary UAVs are employed to perform as relay or edge computing node. To improve the system performance, the task processing model selection, the communication resource allocation, the UAV selection and task migration are jointly optimized. We design a QMIX-based multi-agent deep reinforcement learning algorithm to find the final optimal solutions. Simulation results shows that the proposed algorithm has better convergence and lower system costs, compared with the current existing algorithms.