Artificial bee colony using opposition-based learning

Abstract

To overcome the drawbacks of artificial bee colony(ABC) algorithm that converges slowly in the process of searching and easily suffers from premature, this paper presents an effective approach, called ABC using opposition-based learning(OBL-ABC). It generates opposite solution by the employed bee and onlooker bee, and chooses the better solution as the new locations of employed bee and onlooker bee according to the greedy selection strategy in order to enlarge the search areas; the new approach proposes a new update rule which can retain the advantages of employed bee and onlooker bee and improve the exploration of OBL-ABC. Experiments are conducted on a set of test functions to verify the performance of OBL-ABC, the results demonstrate promising performance of our method OBL-ABC on convergence and it is suitable for solving the optimization of complex functions.