.png){kind=icon}
.png){kind=icon}
Return
An efficient algorithm for high-dimensional function optimization
.png){kind=icon}
PRE
AI
DOI：10.1007/s00500-013-0984-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To solve high-dimensional function optimization problems, many evolutionary algorithms have been proposed. In this paper, we propose a new cooperative coevolution orthogonal artificial bee colony (CCOABC) algorithm in an attempt to address the issue effectively. Cooperative coevolution frame, a popular technique in evolutionary algorithms for large scale optimization problems, is adopted in this paper. This frame decomposes the problem into several subcomponents by random grouping, which is a novel decomposition strategy mainly for tackling nonseparable functions. This strategy can increase the probability of grouping interacting variables in one subcomponent. And for each subcomponent, an improved artificial bee colony (ABC) algorithm, orthogonal ABC, is employed as the subcomponent optimizer. In orthogonal ABC, an Orthogonal Experimental Design method is used to let ABC evolve in a quick and efficient way. The algorithm has been evaluated on standard high-dimensional benchmark functions. Compared with other four state-of-art evolutionary algorithms, the simulation results demonstrate that CCOABC is a highly competitive algorithm for solving high-dimensional function optimization problems.
Keywords:
Cooperative coevolution
Random grouping
OED
High dimension
Artificial bee colony algorithm