.png){kind=icon}
返回
A Cooperative Multistep Mutation Strategy for Multiobjective Optimization Problems With Deceptive Constraints
.png){kind=icon}
PRE
AI
DOI：10.1109/TSMC.2024.3427864.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Constrained multiobjective optimization problems with deceptive constraints (DCMOPs) are a kind of complex optimization problems and have received some attention. For DCMOPs, the closer a solution is to the feasible region, the larger its constraint value. Moreover, multiple local infeasible regions will have different minimal constraint values according to their distances to feasible regions. Therefore, most of the existing algorithms are easy to fall into local regions, and even cannot find any feasible solution. To address DCMOPs, this article proposes a new evolutionary multitasking algorithm with a cooperative multistep mutation strategy. In this algorithm, the DCMOP is transformed into a multitasking optimization problem, in which the main task is the original DCMOP and the created auxiliary task aims to provide effective help for solving the main task. Specially, the designed cooperative multistep mutation strategy contains two contributions to solve deceptive constraints. First, a multistep mechanism is proposed, in which the individuals will use multiple different steps to generate the multiple offspring solutions along one direction, so as to expand search range to find feasible regions. Second, a cooperative mechanism between the two tasks is proposed, in which the main purpose is to provide effective and stable search directions. To be specific, an opposite solution generation method is utilized to generate the opposite solution of auxiliary population in the search space, and the direction from the auxiliary population to the main population will be formed. Combined with these two mechanisms, the proposed cooperative multistep mutation strategy can effectively improve the population diversity along the promising and stable search directions. In the experiments, the proposed algorithm is tested on the two benchmark DCMOPs, which contain objective space constraints and decision space constraints respectively. The results show the effectiveness and superiority of the proposed algorithm over the latest compared algorithms.
Keyword:
Optimization
Task analysis
Shape
Search problems
Multitasking
Convergence
Space exploration
Constrained multiobjective optimization
cooperative
deceptive constraints
evolutionary multitasking (EMT)
multistep mutation strategy
opposite solution generation method
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
暂无机构信息
引用论文
.png){kind=icon}
Evolutionary Multitasking with Global and Local Auxiliary Tasks for Constrained Multi-Objective Optimization具有全局和局部辅助任务的进化多任务处理，用于约束多目标优化
PREAI
分享收藏
PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective OptimizationPlatEMO: 用于进化多目标优化的MATLAB平台
OAAI
OAAI分享收藏Planktonic food and foraging of Eubalaena australis, on Peninsula Valdés (Argentina) nursery groundOAAI
OAAI分享收藏An Evolutionary Multitasking-Based Feature Selection Method for High-Dimensional Classification
PREAI
分享收藏
查看更多内容