一种新的遗传算法在并行机调度问题中的应用  

APPLYING A NEW GENETIC ALGORITHM IN PARALLEL MULTI-MACHINE SCHEDULING PROBLEM

作　　者：高家全[1] 何桂霞[1] 赵端阳[1] 王雨顺[2] 

机构地区：[1]浙江工业大学之江学院,浙江杭州310024 [2]南京师范大学数学与计算机科学学院,江苏南京210097

出　　处：《计算机应用与软件》2008年第8期22-23,26,共3页Computer Applications and Software

基　　金：国家自然科学基金项目(40405019);浙江省教育厅基金(20051436)

摘　　要：针对相同交货期窗口非等同并行机提前/拖后调度问题,设计了一个基于向量组编码的遗传算法。此算法的编码方法简单,能有效地反映实际调度方案,收敛速度快。为适应调度实时性和解大型此类问题的需要,基于遗传算法自然并行性特点的基础上,实现了主从式控制网络模式下并行遗传算法。仿真结果表明,此算法是有效的,优于普通的遗传算法,具有较高的并行性。In order to solve parallel multi-machine earliness/tardiness scheduling problem with same due date windows, a new genetic algorithm which is based on vector group coding method is designed. The algorithm has following characteristics ： simple coding method and faster convergence speed, effectively reflects the actual scheduling scheme. Under the mode of master-slave control networks, parallel genetic algorithm is applied for adapting to the needs of solving larger scale problems of this kind and problem of real-time scheduling. The simulation results show that it is an effective genetic algorithm with advantages over common ones, and has better parallelism.

关 键 词：提前/拖后 并行遗传算法 相同交货期窗口 调度问题 

分 类 号：O242.23[理学—计算数学] O224[理学—数学]