Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (10): 56-59.

• 研究、探讨 • Previous Articles     Next Articles

Parallel task scheduling algorithm using improved genetic algorithm

YUAN Xueli1,ZHONG Mingyang2   

  1. 1.The First Affiliated Hospital of Chongqing Medical University,Network Information Center,Chongqing 400016,China
    2.College of Software,Chongqing University,Chongqing 400044,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-04-01 Published:2011-04-01

改进遗传算法的并行任务调度

袁雪莉1,钟明洋2   

  1. 1.重庆医科大学 附属第一医院网络信息中心,重庆 400016
    2.重庆大学 软件学院,重庆 400044

Abstract: Parallel task scheduling is NP-complete problem,which focuses on resource allocation and parallel task schedule,requiring high-performance scheduling algorithm and high-quality solutions.The paper presents a parallel task scheduling algorithm based on improved genetic algorithm,which introduces vector matrix to represent task,resource and scheduling relationship,and use heuristics when original colony is initialized,improving the quality of initial colony.And it adopts rule-bound crossover and mutation operation to improve individual quality.Besides,it proposes an evolution acceleration strategy to?avoid the premature effectively.Simulation result suggests that the algorithm can solve the parallel task scheduling problems effectively.

Key words: Genetic Algorithm(GA), parallel task scheduling, task vector matrix, evolution acceleration strategy

摘要: 并行任务调度是一个NP完全问题,它关注资源的分配和并行任务调度,要求具有高性能的调度算法,且能求解出高质量的解。提出了一种基于改进遗传算法的并行任务调度算法,在算法初始化种群产生时引入任务向量矩阵来表示任务、资源以及调度的关系,并采用启发式方法得到初始化种群,提高种群质量;采用规则约束的交叉和变异操作,提高个体的质量;提出了加速进化策略,有效地避免了早熟。仿真实验结果表明,该改进算法能更有效地求解并行任务调度问题。

关键词: 遗传算法, 并行任务调度, 任务向量矩阵, 加速进化策略