Knowledge-Base Constrained Optimization Evolutionary Algorithm and its Applications

2014 ◽  
Vol 536-537 ◽  
pp. 476-480 ◽  
Author(s):  
Wen Long
Keyword(s):  
Evolutionary Algorithms ◽  
Constrained Optimization ◽  
Evolutionary Algorithm ◽  
Knowledge Base ◽  
Optimization Problem ◽  
Optimization Problems ◽  
Engineering Optimization ◽  
Constrained Optimization Problems ◽  
Single Constraint ◽  
Handling Technique

The most existing constrained optimization evolutionary algorithms (COEAs) for solving constrained optimization problems (COPs) only focus on combining a single EA with a single constraint-handling technique (CHT). As a result, the search ability of these algorithms could be limited. Motivated by these observations, we propose an ensemble method which combines different style of EA and CHT from the EA knowledge-base and the CHT knowledge-base, respectively. The proposed method uses two EAs and two CHTs. It randomly combines them to generate novel offspring individuals during each generation. Simulations and comparisons based on four benchmark COPs and engineering optimization problem demonstrate the effectiveness of the proposed approach.

Composite Evolutionary Algorithm for Constrained Optimization

2012 ◽  
Vol 220-223 ◽  
pp. 2846-2851
Author(s):  
Si Lian Xie ◽  
Tie Bin Wu ◽  
Shui Ping Wu ◽  
Yun Lian Liu
Keyword(s):  
Evolutionary Algorithms ◽  
Constrained Optimization ◽  
Evolutionary Algorithm ◽  
Selection Criteria ◽  
Optimization Problems ◽  
Experimental Results ◽  
Constrained Optimization Problems ◽  
Mutation Operators ◽  
Single Operator ◽  
Algorithm Framework

Evolutionary algorithms are amongst the best known methods of solving difficult constrained optimization problems, for which traditional methods are not applicable. Due to the variability of characteristics in different constrained optimization problems, no single evolutionary with single operator performs consistently over a range of problems. We introduce an algorithm framework that uses multiple search operators in each generation. A composite evolutionary algorithm is proposed in this paper and combined feasibility rule to solve constrained optimization problems. The proposed evolutionary algorithm combines three crossover operators with two mutation operators. The selection criteria based on feasibility of individual is used to deal with the constraints. The proposed method is tested on five well-known benchmark constrained optimization problems, and the experimental results show that it is effective and robust

HYBRID-FITNESS FUNCTION EVOLUTIONARY ALGORITHM BASED ON SIMPLEX CROSSOVER AND PSO MUTATION FOR CONSTRAINED OPTIMIZATION PROBLEMS

2009 ◽  
Vol 23 (01) ◽  
pp. 115-127 ◽  
Author(s):  
YIBO HU
Keyword(s):  
Constrained Optimization ◽  
Evolutionary Algorithm ◽  
Penalty Function ◽  
Feasible Solution ◽  
Optimization Problems ◽  
Fitness Function ◽  
Benchmark Problems ◽  
Crossover Operator ◽  
Hybrid Fitness ◽  
Constrained Optimization Problems

For constrained optimization problems, evolutionary algorithms often utilize a penalty function to deal with constraints, even if it is difficult to control the penalty parameters. To overcome this shortcoming, this paper presents a new penalty function which has no parameter and can effectively handle constraint first, after which a hybrid-fitness function integrating this penalty function into the objective function is designed. The new fitness function can properly evaluate not only feasible solution, but also infeasible one, and distinguish any feasible one from an infeasible one. Meanwhile, a new crossover operator based on simplex crossover operator and a new PSO mutation operator are also proposed, which can produce high quality offspring. Based on these, a new evolutionary algorithm for constrained optimization problems is proposed. The simulations are made on ten widely used benchmark problems, and the results indicate the proposed algorithm is effective.

Sign in / Sign up

Export Citation Format

Share Document