• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2007, Vol. 29 ›› Issue (1): 76-78.

• 论文 • 上一篇    下一篇

基于混合思维进化计算的网格资源分配算法

刘洋 苏德富   

  • 出版日期:2007-01-01 发布日期:2010-05-30

  • Online:2007-01-01 Published:2010-05-30

摘要:

分布式、异构的网格环境中独立计算任务的有效调度是一个关键问题。由于在这样的环境中找到一个最优的调度是一个NP难问题,通常运用各种启发式算法来找到近似最优解 。本文将思维进化计算和禁忌搜索算法结合起来,充分发挥各自的优势,并用实验证明了运用混合思维进化计算进行网格资源分配的有效性。

关键词: 网格 资源分配 思维进化计算 禁忌搜索

Abstract:

The efficient scheduling of the independent tasks in a distributed heterogeneous grid environment is clearly important. Finding an optimal scheduling  for such an environment is a NP-hard problem, and so heuristic approaches must be used in general to get an optimal approximation solution. In this pape  r, we combine the mind evolutionary computation and the tabu search to fully exert respective advantages.Experiments show that it is effective to use the hybrid mind evolutionary computation to solve the problem of grid resource allocation.

Key words: grid;resource allocation;mind evolutionary computation;tabu search