摘要
数据分发管理是HLA/RTI中的一项服务,在大规模的分布式仿真中用来管理状态更新和交互信息的分发,以此限制数据交换的总量.介绍目前数据分发管理的基本方法的基础上,分析了它们的优缺点,提出了一种基于网格的双层数据过滤方法.通过探测数据分布情况,利用双层网格精细过滤数据,减少冗余数据发送量.实验表明,在大规模和复杂环境下此方法具有更好的适应性、可扩展性和更高的性能.
Data distribution management (DDM)is a high level architecture/run-time infrastructure(HLA/RTI)service that manages the distribution of state updates and interaction information in large-scale distributed simulations by limiting and controlling the volume of data exchanged.The grid-based approach DDM as well as its advantages and disadvantages was discussed,and an improved data filtering algorithm based on grid was proposed.Through detecting the distribution of data,the data was refined by the double-level grid to reduce the amount of redundant data.The simulation result shows that in large-scale or complicated situations the improved data filtering approach has better adaptability,scalability and performance.
基金
Supported by the third Innovation Project of Chinese Academic of Science(KGCX3-SYW-407-03)