摘要
针对基本人工鱼群算法中人工鱼漫无目的随机游动或在非全局极值点的大量聚集和(1+1)-ES的不足,充分利用公告板中的历史最优鱼和(1+1)-ES的优点,提出了一种新的混合优化算法。通过测试函数和应用实例测试验证,结果表明新算法显著提高了基本AFSA和(1+1)-ES的求解质量和运行效率,该算法是可行的和有效的。
After analyzing the disadvantages of original Artificial Fish-School Algorithm(AFSA) and (1+1)-Evolution Strategies (ES),a novel hybrid optimization algorithm is proposed.By adding history best fish and remembering (1+1)-ES to original AFSA in evolution process,the ability to break away from the disadvantages of original AFSA is greatly improved.The tests of several classic functions and application models show that the proposed algorithm can greatly improve the ability of seeking the global excellent result and convergence speed and accuracy.h is significantly superior to original AFSA and (1+1)-ES.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第15期51-53,60,共4页
Computer Engineering and Applications
基金
国家民委科学基金资助项目(No.05GX06)
关键词
人工鱼群算法
进化策略
混合优化算法
Artificial Fish School Algorithm(AFSA)
Evolution Strategies(ES)
hybrid optimization algorithm