Many-objective optimisation-based optimal drone deployment for agricultural zone. (20th October 2020)

• Record Type: Journal Article
• Authors: Issad, Hassina Ait; Aoudjit, Rachida; Belkadi, Malika; Rodrigues, Joel J.P.C.
• Is Part Of: International journal of communication networks and distributed systems. Volume 26:Number 1(2021)
• Page Start: 76
• Page End: 98
• Publication Date: 2020-10-20
• Subjects: drones deployment -- coverage problem -- unmanned aerial vehicle -- UAV -- many-objective optimisation -- Pareto front; Computer networks -- Periodicals; Telecommunication systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; 004.6
• Languages: English
• ISSNs: 1754-3916

Abstract

Monitoring using drones is not just a civilian and military task, but it also concerns the agricultural sector, where it can play an important role in the context of smart agriculture. It seems to be a very valuable tool in the future. However, the optimal deployment of a set of monitoring drones is a very challenging problem; it is a NP-Hard problem. In this paper, the deployment problem has been modelled as a constrained many-objective optimisation problem. Powerful heuristics, namely multi-objective artificial bee colony (MOABC), multi-objective particle swarm optimisation (MOPSO), non-dominated sorting genetic algorithm II (NSGA II), strength Pareto evolutionary algorithm II (SPEA II) and non-dominated sorting genetic algorithm III (NSGA III) are used to find the optimal deployment strategy with four goals: minimising energy consumption, maximising total coverage, maintaining connectivity and minimising overlaps. A comparative study was carried out and the results showed that the SPEA II, NSGA III and NSGA II algorithms have better convergence and maintain good diversity than the other algorithms.