基于动态规划算法的二阶段迭代模型任务分布方案的寻优  

The Optimization of Task Distribution Scheme of Two-stage Iterative Model Based on Dynamic Programming Algorithm

作　　者：田启华[1] 董群梅 杜义贤[1] 汪巍巍[1] 文小勇[1] 

机构地区：[1]三峡大学机械与动力学院,湖北宜昌443002

出　　处：《机械设计与研究》2016年第3期85-88,共4页Machine Design And Research

基　　金：国家自然科学基金资助项目(51475265)

摘　　要：针对利用启发式算法求解二阶段迭代模型的最优任务分布方案容易陷入局部最优解的问题,引入具有全局搜索特性的动态规划算法,将二阶段迭代模型任务分布方案的寻优过程划分为若干个子问题,通过各子问题的最优化得到全局最优的任务分布方案,以保证任务执行时间为全局最短,减少设计迭代过程的时间成本。以某照相机的开发为例,通过对基于启发式的寻优和基于动态规划算法的寻优的求解结果比较,说明了后者的有效性。In solving the optimization of task distribution scheme of two-stage iterative model, applying heuristic algorithm is easy to fall into local optimal solution problem and the dynamic programming algorithm with overall search character is introduced in this paper. The optimization process of task distribution scheme of two-stage iterative model is divided into several sub-problems. The global optimal solution can be obtained by optimization of each sub-problem. Therefore, the shortest task execution time and the lowest design iterative process time costs could be made certain through the above methods. Taking one camera＇s development process as a sample, the optimal task distribution schemes are solved based on both algorithms and it is proved that the scheme based on the dynamic programming algorithm is more effective.

关 键 词：二阶段迭代模型 任务分布 动态规划 执行时间 寻优 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]