| Title | Evolving Dynamically Reconfiguring UAV-hosted Mesh Networks |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Dubey, R., Louis, S. J., Sengupta, S. |
| Conference Name | 2020 IEEE Congress on Evolutionary Computation (CEC) |
| Date Published | jul |
| Keywords | autonomous aerial vehicles, Bandwidth, bandwidth requirements, Base stations, Batteries, composability, control engineering computing, different user distributions, distributed control, evolutionary adaptive network deployment algorithm, evolving dynamically reconfiguring UAV-hosted mesh networks, flying network base stations, genetic algorithm, genetic algorithms, initial deployment, MESH network, Mesh networks, Metrics, mobile radio, mobile robots, network lifetime, optimisation, overwatch, path planning, potential field parameters, potential fields, pubcrawl, quick temporary networked communications capabilities, remote areas, remotely operated vehicles, reposition UAVs, Resiliency, scouting, security, Training, tuned potential fields, UAV network, unmanned aerial vehicles, unmanned aerial vehicles networks, user bandwidth coverage, user bandwidth needs, Wireless Mesh Network Security, Wireless sensor networks |
| Abstract | We use potential fields tuned by genetic algorithms to dynamically reconFigure unmanned aerial vehicles networks to serve user bandwidth needs. Such flying network base stations have applications in the many domains needing quick temporary networked communications capabilities such as search and rescue in remote areas and security and defense in overwatch and scouting. Starting with an initial deployment that covers an area and discovers how users are distributed across this area of interest, tuned potential fields specify subsequent movement. A genetic algorithm tunes potential field parameters to reposition UAVs to create and maintain a mesh network that maximizes user bandwidth coverage and network lifetime. Results show that our evolutionary adaptive network deployment algorithm outperforms the current state of the art by better repositioning the unmanned aerial vehicles to provide longer coverage lifetimes while serving bandwidth requirements. The parameters found by the genetic algorithm on four training scenarios with different user distributions lead to better performance than achieved by the state of the art. Furthermore, these parameters also lead to superior performance in three never before seen scenarios indicating that our algorithm finds parameter values that generalize to new scenarios with different user distributions. |
| DOI | 10.1109/CEC48606.2020.9185639 |
| Citation Key | dubey_evolving_2020 |
Evolving Dynamically Reconfiguring UAV-hosted Mesh Networks