基于分布式遗传算法的移动Agent迁移策略

Migration Strategy for Mobile Agent Based on Distributed Genetic Algorithm

迁移策略是移动Agent(Mobile Agent,MA)的核心技术之一,MA的效率很大程度上取决于迁移策略的优化。本文提出了一种改进的分布式遗传算法(EDGA),用于对多约束条件下MA迁移策略最优问题进行求解。EDGA将分布式遗传算法和Cascade模型相结合,在迁移算子部分设计一个中心监控器,观察每个子种群的进化,并对迁移个体的选择以及相应子种群的大小做出调整,使进化能力好的子种群得到更大的空间来搜索最优值。实验结果表明:本文所提出的EDGA算法在求解速度和质量上取得了较大的改善。

Migration strategy is one of the most critical problems in the system based on mobile Agent, the efficiency of mobile Agent depends on the optimal migration strategy. This paper proposes a new genetic Algorithm, called Extended Distributed Genetic Algorithms （EDGA）, for multiple constrained migration strategy of mobile Agent. EDGA combines the advantages of Distributed Genetic Algorithms with Cascade Model. We design a central monitor dynamically allotting the size of sub-populations according to their performance, directing the migration, therefore making the searching of routes converge to the global optimization faster and better. The result of the experiments shows that the method is more effective than others.