Multi-start genetic algorithm for preventing UV-phenomenon

In recent years, it is reported that there are many problems with UV-structure, in real problems, such as a lens design problem and protein structure presumption. The fatal performance fall of a genetic algorithm (GA) is caused by UV-phenomenon. Although research has been done so far in order to avoid UV-phenomenon, dissatisfaction was in accuracy or the quantity of use resources. In this paper, we propose a Multi-start Genetic Algorithm (MGA) which is the new evolutionary computation of performing GA of a small scale excellent in local search two or more times. And. we tested this method to optimization of the Fletcher & Powell function (FP function) which is a function with typical UV-structure, and proved the high reliability and saving-resources.