Title A distributed PSO-based exploration algorithm for a UAV network assisting a disaster scenario
External publication No
Means Future Gener Comput Syst
Scope Article
Nature Científica
JCR Quartile 1
SJR Quartile 1
JCR Impact 6.12500
Area International
Web https://www.scopus.com/inward/record.uri?eid=2-s2.0-85051027885&doi=10.1016%2fj.future.2018.07.048&partnerID=40&md5=b3101c704c0657ef45db291cca240401
Publication date 01/01/2019
ISI 000446283600011
Scopus Id 2-s2.0-85051027885
DOI 10.1016/j.future.2018.07.048
Abstract UAV networks have been in the spotlight of the research community on the last decade. One of the civil applications in which UAV networks may have more potential is in emergency response operations. Having a UAV network that is able to deploy autonomously and provide communication services in a disaster scenario would be very helpful for both victims and first responders. However, generating exploratory trajectories for these networks is one of the main issues when dealing with complex scenarios. We propose an algorithm based on the well-known Particle Swarm Optimization algorithm, in which the UAV team follows the networking approach known as Delay Tolerant Network. We pursue two main goals, the first is exploring a disaster scenario area, and the second is making the UAVs converge to several victims groups discovered during the exploration phase. We have run extensive simulations for performing a characterization of the proposed algorithm. Both goals of the mission are successfully achieved with the proposed algorithm. Besides, in comparison to an optimal trajectory planning algorithm that sweeps the entire disaster scenario, our algorithm is able to discover faster the 25%, 50% and 75% of the scenario victims and it converges faster. In addition, in terms of connections events between a victim and a UAV, our algorithm shows more frequent connections and less time between consecutive connections. (C) 2018 Elsevier B.V. All rights reserved.
Keywords Particle Swarm Optimization; Unmanned Aerial Vehicle network; AANET; Disaster scenario
Universidad Loyola members