摘要： 针对传统蚁群算法容易出现早熟和停滞现象，提出了一种多蚁群伪并行优化算法，将蚁群分成若干个子蚁群，在各子蚁群中引入信息素平滑机制，通过设计迁移算子，使多个子蚁群并行、协同寻优，从而使算法跳离局部最优解。类比实验表明，该算法比传统的蚁群算法具有更好的搜索全局最优解的能力。
关键词:
蚁群算法,
信息素平滑,
迁移算子,
多蚁群
Abstract: To overcome the limitation of precocity and stagnation in classical ant colony algorithm, this paper presents a multi-ant colony virtual parallel optimization algorithm. The ant colony is divided into several children ant colonies, and the pheromone flatness system is used in each child ant colony. By designing an immigrant operator, the parallel and cooperating optimization of children ant colonies ate obtained. Contrastive experiments show that the algorithm has a better capability of global optimization than traditional ant colony algorithm.
Key words:
ant colony algorithm,
pheromone flatness,
immigrant operator,
multi-ant colony
中图分类号:
刘利强;袁赣南;戴运桃. 多蚁群伪并行优化算法[J]. 计算机工程, 2007, 33(23): 199-201.
LIU Li-qiang; YUAN Gan-nan; DAI Yun-tao. Multi-ant Colony Virtual Parallel Optimization Algorithm[J]. Computer Engineering, 2007, 33(23): 199-201.