Applied Artificial Intelligence (Sep 2019)

A Pheromonal Artificial Bee Colony (pABC) Algorithm for Discrete Optimization Problems

  • Dursun Ekmekci

DOI
https://doi.org/10.1080/08839514.2019.1661120
Journal volume & issue
Vol. 33, no. 11
pp. 935 – 950

Abstract

Read online

The Artificial Bee Colony (ABC) algorithm, which simulates the intelligent foraging behavior of the honeybee colony, is one of the most preferred swarm intelligence-based metaheuristic methods for combinatorial optimization problems. In this study, the local search ability of the ABC algorithm, which can be spread to different regions of the solution space, is developed with the pheromone approach of ant colony optimization (ACO). The effects of the method, named pheromonal ABC (pABC), to the standard ABC and its competitiveness with other metaheuristic methods was presented with testing with popular benchmark problems in the NP-hard problem class. For 40 different benchmark problems, while 15 results with ABC have reached the most successful results were obtained in the literature, 25 results obtained with pABC have reached to literature. While ABC best results were behind literature with a percentage of up to 1.12%, pABC best results were behind the percentage of up to 0.63%