遗传算法中自适应方法的比较和分析

Comparison and analysis of adaptive genetic algorithms

分析了前人提出的具有代表性的自适应遗传算法,使用23个测试函数对SGA和3种AGA进行实验比较,讨论并总结出各种AGA的优劣所在,为新研究理念的提出提供基础,也为工业应用提供一个参考标准。实验结果表明,基于聚类分析的AGA在算法性能上较其它自适应遗传算法更优,具有很高的实用价值和发展前景。

The representative adaptive genetic algorithms are analyzed. The performance ofthe SGA and three types ofAGA is compared by testing 23 benchmark functions. The characteristics of the AGA are discussed and concluded, in order to provide reference basis for theoretical research and industrial applications. The result of experiment shows that the clustering-based AGA outperforms the other adaptive genetic algorithms, indicating its great potential in practice and the bright future.