.png){kind=icon}
.png){kind=icon}
Return
Adaptive multiobjective differential evolution based on parallel cell coordinate system
.png){kind=icon}
PRE
AI
DOI：10.1007/s10586-025-05203-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In Multiobjective Differential Evolution (MODE) algorithms, many techniques of balancing between convergence-divergence and exploration–exploitation issues have been investigated. These techniques include archive maintenance, selection mechanism, population size, and proper parameter setting. There are very few MODE algorithms that use feedback information extracted from the evolutionary environment to create an adaptive balance between exploitation and exploration. As a result, this study describes a novel adaptive MODE algorithm based on a parallel cell coordinate system. The proposed algorithm, known as pccs Adaptive Cross-Generation Differential Evolution (pccsACGDE), utilizes information from two consecutive generations and a parallel cell coordinate system to adaptively adjust the parameters. The pccsACGDE algorithm also introduces two new mutation operators in order to better balance exploitation and exploration. To demonstrate the ability of the pccsACGDE algorithm compared to other algorithms, 34 benchmark functions consisting of constraint and unconstraint problems are considered. The outcomes of the simulation demonstrate that the pccsACGDE algorithm has been more successful in producing superior solutions than state-of-the-art methods.
Keywords:
Multiobjective evolutionary algorithms
Differential evolution
Parallel cell coordinate system
Adaptive parameter control
Journal
C
IF:
0
Papers:
691
Citations:
1