A five-step drone collaborative planning approach for the management of distributed spatial events and vehicle notification using multi-agent systems and firefly algorithms

In spite of the performance that existing approaches for drone collaborative planning have demonstrated, there is still a need for new solutions which are capable of effectively identifying the right tasks for the right drones at the right times while maximizing the total benefits obtained from the...

Full description

Saved in:
Bibliographic Details
Published in:Computer networks (Amsterdam, Netherlands : 1999) Netherlands : 1999), 2021-10, Vol.198, p.108282, Article 108282
Main Authors: Gharrad, Hana, Jabeur, Nafaa, Yasar, Ansar Ul-Haque, Galland, Stephane, Mbarki, Mohammed
Format: Article
Language:English
Subjects:
Algorithms
Collaboration
Collaborative planning
Cost benefit analysis
Drone collaboration
Energy consumption
Firefly algorithm
Heuristic methods
Intelligent transportation system
Intelligent transportation systems
Multi-agent systems
Multiagent systems
Traffic flow
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In spite of the performance that existing approaches for drone collaborative planning have demonstrated, there is still a need for new solutions which are capable of effectively identifying the right tasks for the right drones at the right times while maximizing the total benefits obtained from the drones’ actions. These new solutions should be particularly tested within the context of intelligent transportation systems to assess their impact on mobility and traffic flow. In order to address these issues, we present in this paper a new a five-step solution for drone collaborative planning. Our solution uses a Multi-Agent System as well as a Firefly Algorithm solution to enable drones jointly neutralize ongoing events by considering trust factors and cost/benefit analysis. The solution, which is also capable of issuing appropriate warnings to vehicles to prevent them from incurring any undesirable/dangerous impact due to ongoing events, is using a reward-driven competition to encourage drones to join collaborating teams. Our simulations are showing promising results in terms of processing time, energy consumption, and total reward obtained compared to two other planning approaches relaying on random and priority-based selection of the next locations that drones will visit respectively.
ISSN:1389-1286
1872-7069
DOI:10.1016/j.comnet.2021.108282