带免疫变异的蚁群优化算法  

Ant Colony Algorithm with Immune Mutation

作　　者：刘好斌[1] 胡小兵[1] 赵吉东[1] 

机构地区：[1]重庆大学数理学院,重庆400044

出　　处：《计算机仿真》2010年第12期221-223,240,共4页Computer Simulation

基　　金：重庆市自然科学基金(CSPC;2005BB2197);重庆大学高层次人才科研启动基金(020800110420)

摘　　要：研究算法寻优的问题时,传统的蚁群优化算法在寻优过程中存在一定缺陷,如容易陷入停滞状态,收敛速度慢。结合免疫算法和蚁群算法的优点,为提高精度和运算速度,提出一种基于免疫算法的蚁群优化算法。采用搜索解的过程中对概率选择规则采用了对比度增强技术,以加快算法的收敛速度;并融入选择算子进行搜索,根据先验知识提出了免疫变异策略,提高算法的全局性能。仿真结果表明,改进算法具有很好的稳定性和全局优化性能,有效地防止停滞现象,加快了算法的收敛速度。There are certain shortcomings in ant colony algorithm,such as failing into stagnation and slow convergence.Combining the advantages of immune algorithm and ant colony algorithm,a novel ant colony algorithm based on immune algorithm is proposed.In order to speed up the convergence speed,the algorithm makes use of contrast enhancement technology in the search process of solution of the probability,introduces selection operators and then initiates immunity strategies based on priori knowledge.The simulation results show that the improved algorithm performs favorable stability and global optimization,and it can avoid stagnation phenomenon in effective and accelerate the convergence speed.

关 键 词：蚁群算法 免疫算法 变异策略 路径选择 旅行商问题 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]