S.S. Bacanli, F. Cimen, E. Elgeldawi, and D. Turgut

Placement of Package Delivery Center for UAVs with Machine Learning


Cite as:

S.S. Bacanli, F. Cimen, E. Elgeldawi, and D. Turgut. Placement of Package Delivery Center for UAVs with Machine Learning. In Proc. of IEEE GLOBECOM 2021, December 2021.

Download:

Download 

Abstract:

Unmanned aerial vehicles (UAVs) are widely used in many application areas within opportunistic networks. In this paper, we investigate the charging station placement problem in the application scenario with ten UAVs deployed in an opportunistic network environment. We have used a real-world dataset that contains human mobility traces from North Carolina State University. The UAVs cruise on the network with spiral shapes and distribute messages to the nodes on the ground. The charging station locations are generated with random, Density-based spatial clustering of applications with noise (DBSCAN) and kmeans clustering approaches. The evaluation results indicate that the k-means algorithm with three clusters outperformed the other two methods in terms of the success rates and the message delay.

BibTeX:

@inproceedings{Bacanli-2021-GLOBECOM,
	author = "S.S. Bacanli and F. Cimen and E. Elgeldawi and D. Turgut",
	title = "Placement of Package Delivery Center for UAVs with Machine Learning",
	booktitle = "Proc. of IEEE GLOBECOM 2021",
	year = "2021",
	month = "December",
	abstract = {Unmanned aerial vehicles (UAVs) are widely used in many application areas within opportunistic networks. In this paper, we investigate the charging station placement problem in the application scenario with ten UAVs deployed in an opportunistic network environment. We have used a real-world dataset that contains human mobility traces from North Carolina State University. The UAVs cruise on the network with spiral shapes and distribute messages to the nodes on the ground. The charging station locations are generated with random, Density-based spatial clustering of applications with noise (DBSCAN) and kmeans clustering approaches. The evaluation results indicate that the k-means algorithm with three clusters outperformed the other two methods in terms of the success rates and the message delay.   },
}

Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Sun Mar 03, 2024 18:41:16