New Multi-Objective Constrained Optimization Evolutionary Algorithm

In this paper, a new evolutionary algorithm (EA) to solve multi-objective constrained optimization problem (MCOP) is proposed. First, the rank of the individual and the scalar constraint violation of the individual are defined. Then, based on the rank and the scalar constraint violation of the indiv...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2008 3rd International Conference on Innovative Computing Information and Control s. 320
Hlavní autor: Chun-An Liu
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2008
Témata:
Distance measurement
Evolutionary computation
Genetic algorithms
Optimization
Probability
Simulation
Switches
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, a new evolutionary algorithm (EA) to solve multi-objective constrained optimization problem (MCOP) is proposed. First, the rank of the individual and the scalar constraint violation of the individual are defined. Then, based on the rank and the scalar constraint violation of the individual, a new fitness function and a switch selection operator are presented. Accordingly, when the individuals are evaluated or ranked, it doesn't need to care about the feasibility of individuals, therefore it is a penalty-parameterless constraint-handling approach for multi-objective constrained optimization problem. Finally, the computer simulations demonstrate the effectiveness of the proposed algorithm.
DOI:10.1109/ICICIC.2008.387