| Autor: |
Mongay Batalla J; Department of Telecommunications, Warsaw University of Technology, 00-661 Warsaw, Poland., Mavromoustakis CX; Department of Computer Science, University of Nicosia, 24005 Nicosia, Cyprus., Mastorakis G; Department of Management Science and Technology, Hellenic Mediterranean University, 72100 Crete, Greece., Markakis EK; Department of Electrical and Computer Engineering, Hellenic Mediterranean University, 72100 Crete, Greece., Pallis E; Department of Electrical and Computer Engineering, Hellenic Mediterranean University, 72100 Crete, Greece., Wichary T; Department of Telecommunications, Warsaw University of Technology, 00-661 Warsaw, Poland., Krawiec P; Department of Internet Services and Applications, National Institute of Telecommunications, 04-894 Warsaw, Poland., Lekston P; FlyTech UAV Sp. z o.o., 30-149 Kraków, Poland. |
| Abstrakt: |
This paper proposes a two-phase algorithm for multi-criteria selection of packet forwarding in unmanned aerial vehicles (UAV), which communicate with the control station through commercial mobile network. The selection of proper data forwarding in the two radio link: From UAV to the antenna and from the antenna to the control station, are independent but subject to constrains. The proposed approach is independent of the intra-domain forwarding, so it may be useful for a number of different scenarios of Unmanned Aerial Vehicles connectivity (e.g., a swarm of drones). In the implementation developed in this paper, the connection is served by three different mobile network operators in order to ensure reliable connectivity. The proposed algorithm makes use of Machine Learning tools that are properly trained for predicting the behavior of the link connectivity during the flight duration. The results presented in the last section validate the algorithm and the training process of the machines. |
