A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary Algorithm
Many-objective optimization problems (MaOPs) present a huge challenge to the traditional Pareto-based multi-objective algorithms because the increase of the objectives results in the low-efficiency of the Pareto dominance in distinguishing the relationships between the solutions during the environme...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8730321/ |
| _version_ | 1818878081933246464 |
|---|---|
| author | Junhua Liu Yuping Wang Shiwei Wei Xiangjuan Wu Wuning Tong |
| author_facet | Junhua Liu Yuping Wang Shiwei Wei Xiangjuan Wu Wuning Tong |
| author_sort | Junhua Liu |
| collection | DOAJ |
| description | Many-objective optimization problems (MaOPs) present a huge challenge to the traditional Pareto-based multi-objective algorithms because the increase of the objectives results in the low-efficiency of the Pareto dominance in distinguishing the relationships between the solutions during the environmental selection. To enhance the selection pressure, in this paper, through redefining each objective function by a non-linear transformation, we first propose a new dominance method called NLAD-dominance, in which a dynamic parameter adjusting scheme is designed to dynamically adjust parameter α according to different numbers of objectives and different evolutionary states. As a result, NLAD-dominance can provide proper selection pressure for different kinds of MaOPs in different stages of evolution. Then, based on NLAD-dominance, we design a new fitness estimation strategy which takes both convergence and diversity into account, and adaptively balances them by a parameterless penalty rule. Thus, it can well evaluate the quality of each solution. At last, we conduct the experiments and compare the proposed algorithm with five state-of-the-art algorithms on 80 test instances of 16 benchmark problems with up to 20 objectives. The experimental results indicate that the proposed algorithm is highly competitive in terms of both convergence enhancement and diversity maintenance. |
| first_indexed | 2024-12-19T14:08:31Z |
| format | Article |
| id | doaj.art-3f40327d8b2945f09df817416baeeec9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T14:08:31Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3f40327d8b2945f09df817416baeeec92022-12-21T20:18:14ZengIEEEIEEE Access2169-35362019-01-017817018171610.1109/ACCESS.2019.29206988730321A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary AlgorithmJunhua Liu0https://orcid.org/0000-0002-2791-9581Yuping Wang1Shiwei Wei2Xiangjuan Wu3Wuning Tong4School of Computer Science and Technology, Xidian University, Xi’an, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an, ChinaSchool of Computer and Technology, Guilin University of Aerospace Technology, Guilin, ChinaSchool of Computer Science and Technology, Xidian University, Xi’an, ChinaSchool of Science, Shaanxi University of Chinese Medicine, Xianyang, ChinaMany-objective optimization problems (MaOPs) present a huge challenge to the traditional Pareto-based multi-objective algorithms because the increase of the objectives results in the low-efficiency of the Pareto dominance in distinguishing the relationships between the solutions during the environmental selection. To enhance the selection pressure, in this paper, through redefining each objective function by a non-linear transformation, we first propose a new dominance method called NLAD-dominance, in which a dynamic parameter adjusting scheme is designed to dynamically adjust parameter α according to different numbers of objectives and different evolutionary states. As a result, NLAD-dominance can provide proper selection pressure for different kinds of MaOPs in different stages of evolution. Then, based on NLAD-dominance, we design a new fitness estimation strategy which takes both convergence and diversity into account, and adaptively balances them by a parameterless penalty rule. Thus, it can well evaluate the quality of each solution. At last, we conduct the experiments and compare the proposed algorithm with five state-of-the-art algorithms on 80 test instances of 16 benchmark problems with up to 20 objectives. The experimental results indicate that the proposed algorithm is highly competitive in terms of both convergence enhancement and diversity maintenance.https://ieeexplore.ieee.org/document/8730321/Balanceable fitness estimationdominance methodconvergencediversitymany-objective optimizationselection pressure |
| spellingShingle | Junhua Liu Yuping Wang Shiwei Wei Xiangjuan Wu Wuning Tong A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary Algorithm IEEE Access Balanceable fitness estimation dominance method convergence diversity many-objective optimization selection pressure |
| title | A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary Algorithm |
| title_full | A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary Algorithm |
| title_fullStr | A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary Algorithm |
| title_full_unstemmed | A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary Algorithm |
| title_short | A Parameterless Penalty Rule-Based Fitness Estimation for Decomposition-Based Many-Objective Optimization Evolutionary Algorithm |
| title_sort | parameterless penalty rule based fitness estimation for decomposition based many objective optimization evolutionary algorithm |
| topic | Balanceable fitness estimation dominance method convergence diversity many-objective optimization selection pressure |
| url | https://ieeexplore.ieee.org/document/8730321/ |
| work_keys_str_mv | AT junhualiu aparameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT yupingwang aparameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT shiweiwei aparameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT xiangjuanwu aparameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT wuningtong aparameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT junhualiu parameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT yupingwang parameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT shiweiwei parameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT xiangjuanwu parameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm AT wuningtong parameterlesspenaltyrulebasedfitnessestimationfordecompositionbasedmanyobjectiveoptimizationevolutionaryalgorithm |