Informatica Logo

INFORMATICA
International Journal

Main Page
Editorial Board
Abstracting/Indexing
Instructions to Authors
Subscription Information


Contents
Author Index
Papers in Production

INFORMATICA, 2017, Vol. 28, No. 3, 415-438
© Institute of Mathematics and Informatics,
DOI: http://dx.doi.org/10.15388/Informatica.2017.136

ISSN 0868-4952

Self-Adaptive and Adaptive Parameter Control in Improved Artificial Bee Colony Algorithm

Bekir AfSAR1, Dogan AYDIN, Aybars UGUR, Serdar KORUKOGLU

Department of Computer Engineering, Dumlupinar University, Kütahya, Turkey, Department of Computer Engineering, Ege University, Izmir, Turkey E-mail: bekirafsar@gmail.com, dogan.aydin@dpu.edu.tr, aybars.ugur@ege.edu.tr, serdar.korukoglu@ege.edu.tr

Abstract

The Improved Artificial Bee Colony (IABC) algorithm is a variant of the well-known Artificial Bee Colony (ABC) algorithm. In IABC, a new initialization approach and a new search mechanism were added to the ABC for avoiding local optimums and a better convergence speed. New parameters were added for the new search mechanism. Specified values of these newly added parameters have a direct impact on the performance of the IABC algorithm. For better performance of the algorithm, parameter values should be subjected to change from problem to problem and also need to be updated during the run of the algorithm. In this paper, two novel parameter control methods and related algorithms have been developed in order to increase the performance of the IABC algorithm for large scale optimization problems. One of them is an adaptive parameter control which updates parameter values according to the feedback coming from the search process during the run of the algorithm. In the second method, the management of the parameter values is left to the algorithm itself, which is called self-adaptive parameter control. The adaptive IABC algorithms were examined and compared to other ABC variants and state-of-the-art algorithms on a benchmark functions suite. Through the analysis of the results of the experiments, the adaptive IABC algorithms outperformed almost all ABC variants and gave competitive results with state-of-the-art algorithms from the literature.

Keywords:

Artificial Bee Colony, Improved Artificial Bee Colony, parameter control methods, adaptive parameter control, self-adaptive parameter control


1Corresponding author.
To preview Lithuanian abstract see full article text

PDFTo preview full article text in PDF format click here

Get Free ReaderYou could obtain free Acrobat Reader from Adobe


TopTop Copyright © INFORMATICA, Vilnius University Institute of Mathematics and Informatics, 2010