Complex network based adaptive artificial bee colony algorithm

Document Type

Conference Proceeding

Department or Administrative Unit

Computer Science

Publication Date



The population dynamics of many evolutionary algorithms exhibit complex network properties. The analysis of such network can be used to obtain the meaningful information about population development in time, making it possible to detect less active members. Drawing from these ideas, the self-adaptive complex network analysis based modification to ABC algorithm was proposed in [1], showing some interesting results. This paper continues with the previous research, further improving the previous algorithm, exploring another approaches towards inactive solutions replacement, as well as more sophisticated mechanism of determining the solutions' value for further development of the population. The efficiency of the new algorithm version is evaluated on various standard continuous optimisation scalable benchmark functions and compared to standard ABC, showing that the modified ABC algorithm outperforms the original in most of the cases.


This article was originally published in 2016 IEEE Congress on Evolutionary Computation (CEC). The full-text article from the publisher can be found here.

Due to copyright restrictions, this article is not available for free download from ScholarWorks @ CWU.


2016 IEEE Congress on Evolutionary Computation (CEC)


Copyright © 2016, IEEE