计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (19): 26-30.DOI: 10.3778/j.issn.1002-8331.2009.19.007

• 博士论坛 • 上一篇    下一篇

智能电网快速仿真与模拟任务调度优化方法

余贻鑫,徐 臣,贾宏杰   

  1. 天津大学 电力系统仿真控制教育部重点实验室,天津 300072
  • 收稿日期:2009-02-06 修回日期:2009-04-07 出版日期:2009-07-01 发布日期:2009-07-01
  • 通讯作者: 余贻鑫

Optimal algorithms for task scheduling on smart grid fast simulation and modeling

YU Yi-xin,XU Chen,JIA Hong-jie   

  1. Key Laboratory of Power System Simulation and Control of Ministry of Education,Tianjin University,Tianjin 300072,China
  • Received:2009-02-06 Revised:2009-04-07 Online:2009-07-01 Published:2009-07-01
  • Contact: YU Yi-xin

摘要: 基于MAS建立的分布并行计算环境,其任务调度问题具有新的特点。对于基于MAS的配电快速仿真与模拟系统,以配电网三相状态估计为例,建立了新的调度问题模型,提出了基于FCM的启发式任务调度优化方法。该方法利用模糊C均值聚类分析算法对独立任务进行聚类分析,避免了在超大解空间中用基于搜索的方法去寻求最优解的做法。该方法具有线性时间复杂度,而且通过大量算例表明它总是能够在合理的时间内获得次优解或最优解,使masDSE的性能有明显改善。

Abstract: In the distributed parallel computing environment based on MAS,some new characteristics has brought forword to the Task Scheduling.Aimed at task scheduling in distribution fast simulation and modeling that is based on MAS,develope a new model for Task Scheduling;Propose a new heuristic task scheduling optimization algorithm based on fuzzy C-means clustering algorithms.This algorithm not only has linear time complexity,but also gets near-optimal solution or optimal solution stably,and significantly improves the performance of masDSE.This conclusion is proved by large number of case test.