COMPARATIVE STUDY OF METAHEURISTICS BASED ON SWARM INTELLIGENCE: WHALE OPTIMIZATION ALGORITHM AND PARTICLE SWARM OPTIMIZATION
Palavras-chave:
Computational Optimization, Metaheuristics, Evolutionary Computation, Whale Optimization Algorithm, Particle Swarm OptimizationResumo
Optimization is the field of studies that seeks to develop techniques to improve processes,
leading them to the best operating scenario. Within the field of optimization studies, the idea of con-
structing new techniques influenced by the adaptation mechanisms of living beings has been developed.
In the context of computation, the construction of bio-inspired algorithms gains notoriety because it al-
lows agents that perform computationally simple tasks to contribute to solve complex problems when
grouped together. This paper presents a comparative study between the metaheuristic techniques based
on swarm intelligence: WOA (Whale Optimization Algorithm) and PSO (Particle Swarm Optimization),
in order to identify among the techniques the algorithm that obtains the best performance, investigating
the influence of the number of individuals of the population, the influence of parameters on computa-
tional cost and execution time, as well as enriching the literature regarding the choice of methods and
parameters according to the determined domains. The algorithms were implemented and benchmark
functions widely known in the literature were used to evaluate the efficiency of the proposed methods
and compare the results obtained. The results demonstrated the optimum performance for the search of
minimums and maximums, and the best parameters for each algorithm.