Title :
An improved Constrained Optimization Genetic Algorithm
Author :
Ye Fei ; Haiyang Yu ; Jiang Xueshou
Author_Institution :
Sch. of Traffic & Mech. Eng., Shenyang Jianzhu Univ., Shenyang, China
Abstract :
This paper analyzed the unreasonable of widespread use of competitive selection rules to solving Constrained Optimization Genetic Algorithm. With the concept of Pareto dominance and the sequence of individual factorial design a new sort of population model. It balances the feasible region and constraints optimal solution search direction, which makes the Constrained Optimization Genetic Algorithm along both sides of feasible region to search for constrained optimal solution. There is a relationship between feasible region in demes and evolutional generation and also the order factor. It considers both the algorithmic search quality and efficiency optimization. The numerical experiment and engineering example have shown, the improved Constrained Optimization Genetic Algorithm has the more simple algorithm structure, the higher solution quality and much more stable.
Keywords :
Pareto optimisation; genetic algorithms; Pareto dominance; algorithmic search quality; competitive selection rule; constrained optimization genetic algorithm; constraints optimal solution; evolutional generation; individual factorial design; population model; Software; Software algorithms; Constrained Optimization; Constrained Optimization Genetic Algorithm; Pareto dominance;
Conference_Titel :
Intelligent Computing and Intelligent Systems (ICIS), 2010 IEEE International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-6582-8
DOI :
10.1109/ICICISYS.2010.5658317