基于代理模型估值不确定度的昂贵多目标优化问题研究
A research for expensive many-objective optimization problem based on uncertainty of surrogate
张晶 1裴东兴 2马瑾 1沈大伟2
作者信息
- 1. 山西财贸职业技术学院物联网技术系,山西 太原 030031
- 2. 中北大学电子测试技术国家重点实验室,山西 太原 030051;中北大学仪器科学与动态测试教育部重点实验室,山西 太原 030051
- 折叠
摘要
针对代理模型辅助的多目标优化算法中个体不确定度之间相互冲突的问题,本文提出个体每个目标估值不确定的填充准则,同时,为了减少训练模型消耗的计算资源,提出基于非支配排序的样本选择算法.为了验证该算法的可行性,采用 DTLZ和 WFG测试函数进行测试,得出结果与近些年发表 5 种具有代表性的同类型算法进行对比,结果说明该算法可以有效的解决昂贵高维高目标优化问题.
Abstract
In surrogate assisted many objective optimization,conflicting uncertainties of surrogate between objective is a challenge.Hence,an many objective optimization algorithm with uncertainty of surrogate is proposed called,US-MOEA.The main work of this paper is as follows:first of all,infill criterion based on the uncertainty of predicted value is proposed to select promising solutions for re-evaluating by expensive optimization objective function.Then,in order to reduce the computational resources,a method based on non-dominated sorting is used to select some individual as train sample.In order to verify the effectiveness of proposed algorithm,the DTLZ and WFG test suits problem are applied and compare with five the-state-of-art algorithms proposed in recent years.The experi-mental results illustrate that the US-MOEA is an effectively method for solving expensive many objective optimization problems.
关键词
进化算法/昂贵多目标优化问题/代理模型/填充准则/不确定度Key words
evolutionary algorithm/expensive many objective optimization problem/surrogate/infill criterion/uncertainty引用本文复制引用
基金项目
国防科技重点实验室基金(61420010402001)
山西省高等学校科技创新项目(2020L0762)
出版年
2024
NETL
NSTL
万方数据