This repository is accompanying the paper "Reinforcement Learning Based Dynamic Power Control for UAV Mobility Management" (Irshad Meer, Karl-L. Besser, Mustafa Ozger, Vincent Poor, and Cicek Cavdar, 2023 Asilomar Conference on Signals, Systems, and Computers, Oct. 2023, pp. 724-728, doi:10.1109/IEEECONF59524.2023.10477032, arXiv:2312.04742).
The following files are provided in this repository:
baseline.py
: Python module that contains the comparison/baseline algorithmsdata_logger.py
: Python module that contains a custom callback for saving data.environment.py
: Python module that contains thegym
environment.loggers.py
: Python module that contains a custom callback for saving data.main_training.py
: Python script that runs the training.movement.py
: Python module that contains the implementation of the stochastic UAV movement model.reliability.py
: Python module that contains functions for calculating the outage probability.test.py
: Python script that runs the testing of the trained model.util.py
: Python module that contains utility functions.
You can use services like CodeOcean or Binder to run the scripts online.
If you want to run it locally on your machine, make sure that Python3 and all required libraries are installed.
This research was supported in part by the CELTIC-NEXT Project, 6G for Connected Sky (6G-SKY), with funding received from Vinnova, Swedish Innovation Agency, by the German Research Foundation (DFG) under grant BE 8098/1-1, and by the U.S National Science Foundation under Grants CNS-2128448 and ECCS-2335876.
This program is licensed under the GPLv3 license. If you in any way use this code for research that results in publications, please cite our original article listed above.
You can use the following BibTeX entry
@article{Meer2023reinforcement,
author = {Meer, Irshad A. and Besser, Karl-Ludwig and Ozger, Mustafa and Poor, H. Vincent and Cavdar, Cicek},
title = {Reinforcement Learning Based Dynamic Power Control for UAV Mobility Management},
booktitle = {2023 57th Asilomar Conference on Signals, Systems, and Computers},
year = {2023},
month = {10},
pages = {724--728},
publisher = {IEEE},
venue = {Pacific Grove, CA, USA},
doi = {10.1109/IEEECONF59524.2023.10477032},
archiveprefix = {arXiv},
eprint = {2312.04742},
primaryclass = {cs.IT},
}