Enhancing artificial bee colony algorithm using inversely proportional mutation

Abstract

Artificial bee colony (ABC) algorithm is a recently invented powerful optimiser. ABC has become very popular in swarm intelligence research area and has the advantages of its few control parameters, simplicity and ease of implementation. However, latest studies have been devoted to the improvement of the exploitation capability of the standard ABC, because ABC is good at exploration but poor at exploitation, and the convergence speed is also an issue in some cases. Motivated by these issues, this paper proposes a modified ABC algorithm that uses an inversely proportional mutation function and a new search mechanism to solve numerical function optimisation problems. The proposed algorithm is applied to a set of nine well–known benchmarks with different dimensions. To verify the performance of the proposed algorithm, it is compared with the standard ABC algorithm. Experimental results demonstrate that the proposed modified ABC algorithm performs much better than the standard ABC algorithm.