@inproceedings{Rosas:2020:10.1109/GCWkshps50303.2020.9367580,
author = {Rosas, De Andraca FE and Azari, M and Arani, A},
doi = {10.1109/GCWkshps50303.2020.9367580},
pages = {1--6},
publisher = {IEEE},
title = {Mobile cellular-connected UAVs: reinforcement learning for sky limits},
url = {http://dx.doi.org/10.1109/GCWkshps50303.2020.9367580},
year = {2020}
}

Download

TY  - CPAPER
AB  - A cellular-connected unmanned aerial vehicle (UAV) faces several key challenges concerning connectivity and energy efficiency. Through a learning-based strategy, we propose a general novel multi-armed bandit (MAB) algorithm to reduce disconnectivity time, handover rate, and energy consumption of UAV by taking into account its time of task completion. By formulating the problem as a function of UAV's velocity, we show how each of these performance indicators (PIs) is improved by adopting a proper range of corresponding learning parameter, e.g. 50% reduction in HO rate as compared to a blind strategy. However, results reveal that the optimal combination of the learning parameters depends critically on any specific application and the weights of PIs on the final objective function.
AU  - Rosas,De Andraca FE
AU  - Azari,M
AU  - Arani,A
DO  - 10.1109/GCWkshps50303.2020.9367580
EP  - 6
PB  - IEEE
PY  - 2020///
SP  - 1
TI  - Mobile cellular-connected UAVs: reinforcement learning for sky limits
UR  - http://dx.doi.org/10.1109/GCWkshps50303.2020.9367580
UR  - https://ieeexplore.ieee.org/abstract/document/9367580
UR  - http://hdl.handle.net/10044/1/103105
ER  - 

Download