Supporting Large-Scale Distributed Simulations Through the Topic-Based Data Distribution Management System
提出一种基于主题的发布-订阅消息系统（TBMS），通过主题匹配替代传统区域匹配，提升分布式仿真中数据分发管理的性能、可靠性和可扩展性，实验评估了利用率和等待时间。
Modeling and Simulation (M&S) is a fundamental technology to design and study complex systems in various industrial and scientific domains when real-world testing is impractical due to costs, safety concerns, and time constraints. To promote the reusability and interoperability of simulation entities, allowing them to interoperate without geographic barriers, distributed simulation has been introduced. One of the most widely adopted standards for distributed simulation is IEEE 1516-2010: High Level Architecture (HLA). Among the services provided by HLA, a key one is Data Distribution Management (DDM), which allows to reduce the transmission and reception of unnecessary data to improve communication effectiveness among simulation entities. This is done by computing the so-called “region matching”, i.e., the overlap between “update” and “subscription” regions. In this article, a novel DDM system called the Topic-based publish-subscribe Messaging System (TBMS) is proposed to improve the performance, reliability, and scalability of DDM services. Unlike traditional algorithms, this system revolves around the concept of “topic” that favors a contextualized approach to the match, avoiding the filtering of the information actually of interest on the receiver side. Experiments have been conducted to evaluate the proposed TBMS in terms of utilization and waiting time metrics.