计算机应用 ›› 2010, Vol. 30 ›› Issue (06): 1679-1681.

• 典型应用 • 上一篇    下一篇

基于并行计算的大规模群体行为建模与仿真方法研究

孟凡亮1,胡晓峰2,蒋亚群3,禹海全3,徐旭林3   

  1. 1. 国防大学信息作战与指挥训练教研部
    2. 中国人民解放军国防大学信息作战与指挥训练教研部
    3.
  • 收稿日期:2009-12-16 修回日期:2010-02-09 发布日期:2010-06-01 出版日期:2010-06-01
  • 通讯作者: 孟凡亮
  • 基金资助:
    国家863计划项目

Research of modeling and simulation method for large scale crowds behavior based on parallel computing

  • Received:2009-12-16 Revised:2010-02-09 Online:2010-06-01 Published:2010-06-01
  • Contact: Meng FanLiang

摘要: 为解决当前群体行为模型因规模扩大而导致计算量剧增的问题,采用并行离散事件方法构建了大规模群体行为模型,利用YH-SUPE仿真引擎实现了群体行为模型的并行计算。重点介绍了模型中仿真对象和仿真对象信息交互的设计方法,并对该模型在不同数量的节点和仿真实体的环境下进行了测试。实验结果表明,将并行计算引入群体行为建模之中,可以显著提高仿真个体的数量,更加有效地支持了群体模型的实时运行。

关键词: 并行计算, 大规模群体行为, YH-SUPE仿真引擎, 并行离散事件仿真

Abstract: To address the problem that the expansion of crowds' behavior model causes sharp increase in computation, this paper presented a parallel discrete event approach for simulating large scale crowds' behavior and realized computation in parallel through YH-SUPE engine. It also provided detailed description of simulation objects and communication between them, and then evaluated the performance of model for different number of simulation objects on different number of processes. The experimental results show that this proposed method can increase the amount of simulation objects and support the model more effectively in real-time.

Key words: parallel computing, large scale crowds simulation, YH-SUPE simulation engine, parallel discrete event simulation