摘要
充分利用前期迭代中解的信息是构造高效蚁群算法实现的关键之一。文中把免疫记忆和克隆选择的思想引入蚁群算法,提出了基于免疫记忆的蚁群算法(IMBACA)。算法通过在原有蚁群模型上增加一个免疫记忆库,将记忆库中的解对应为免疫记忆细胞(及其产生的抗体),将问题对应为抗原,并借鉴克隆选择和免疫记忆的思想进行解的构造和信息素更新。算法从解的质量和时间方面与传统蚁群算法进行了比较,实验结果表明,所提出的IMBACA算法可明显提高传统蚁群算法的性能,同时也为解决其他组合优化问题提出了一个新的思路。
Taking full advantage of the information of the previous solutions is one of the keys for constructing highly effective implementation of ant colony algorithm. This paper proposes an Immune Memory-Based Ant Colony Algorithm（IMBACA） by introducing the idea of immune memory and clone selection into ant colony algorithm.IMBACA adds an immune memory library to the ant colony model,regarding the solutions in the immune memory library as antibodies and the problem as antigen. It uses the above idea for solution construction and pheromone concentration update.IMBACA is compared to the traditional ant colony algorithm in terms of both solution quality and speed.Experimental results indicate that the proposed algorithm can evidently improve the performance of the traditional ant colony algorithm.It also provides a new idea for solving other combinational optimization problems.
出处
《计算机仿真》
CSCD
2007年第10期165-168,共4页
Computer Simulation
关键词
免疫记忆
克隆选择
蚁群算法
Immune memory
Clone selection
Ant colony algorithm
