Equilibrium optimizer of interswarm interactive learning strategy

ABSTRACT

This paper proposes an equilibrium optimiser of interswarm interactive learning strategy to plan the shortest flight path of drones. This paper divide the population into a learning swarm and a learned swarm. When the global best fitness value does not change in consecutive k generations, interswarm interactive learning behaviour is triggered. In addition, this paper also proposes a global optimal disturbance strategy to improve the exploitation capability of particles and balances exploration and exploitation by introducing linearly decreasing inertia weights. The algorithm is tested on 23 benchmark functions, and the test results show that the algorithm has greater advantages.

KEYWORDS:

• Interactive learning
• path planning
• equilibrium optimisation
• meta-heuristic
• unmanned aerial vehicle

Disclosure statement

No potential conflict of interest was reported by the author(s).