Evolutionary constrained optimization with hybrid constraint-handling technique

In constrained optimization evolutionary algorithms (COEAs), constraint-handling technique is used to balance the objective function and constraints, but how to achieve this balance is a very important problem. We found that the information of the population during the evolution process can reflect...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Expert systems with applications Ročník 211; s. 118660
Hlavní autori: Peng, Hu, Xu, Zhenzhen, Qian, Jiayao, Dong, Xiaogang, Li, Wei, Wu, Zhijian
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.01.2023
Predmet:
Differential evolution
Evolutionary constrained optimization
Hybrid constraint-handling technique
Restart mechanism
Differential evolution
Restart mechanism
Evolutionary constrained optimization
Hybrid constraint-handling technique
ISSN:0957-4174, 1873-6793
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In constrained optimization evolutionary algorithms (COEAs), constraint-handling technique is used to balance the objective function and constraints, but how to achieve this balance is a very important problem. We found that the information of the population during the evolution process can reflect the current situation of the population, whether the population are inside the feasible region (feasible situation), or are near the boundary of the feasible region (semi-feasible situation), or far away from the feasible region (infeasible situation). Therefore, corresponding constraint-handling method are designed according to the information of each situation—Hybrid Constraint-handling Technique (HCT). The information of the population evolution process is used by HCT to maintain the objective function and constraints balance, and combines the evolutionary algorithm and HCT to propose ECO-HCT to solve COPs. Meanwhile, in infeasible situation, an elite replacement strategy is proposed to help the population accumulate experience. In addition, a criterion for judging that the population falls into the local optimum in the infeasible region and a simple restart mechanism are designed. They can help the population jump out of the local optimum in the infeasible region and effectively improve the algorithm’s ability to solve complex COPs. The 24 constraint test functions from IEEE CEC2006, the 28 constraint test functions from IEEE CEC2017, and three constrained engineering design problems are used to verify the effectiveness and efficiency of the proposed ECO-HCT. Experimental results show that ECO-HCT has very competitive performance compared with other advanced methods. •The hybrid constraint-handling technique (HCT) is proposed.•The elite replacement strategy is proposed.•Information of the population during the evolution process is used effectively.•The criterion for judging that the population falls into a local optimum is proposed.•The simple population restart mechanism is proposed.
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2022.118660