This study aims to optimise the "spray and wait" protocol in delay tolerant networks (DTNs) to improve the performance of information transmission in emergency situations, especially in car accident scenarios. Due to the intermittent connectivity and dynamic environment of DTNs, traditional routing protocols often do not work effectively. In this study, a machine learning method called random forest was used to identify "high-quality" nodes. "High-quality" nodes refer to those with high message delivery success rates and optimal paths. The high-quality node data was filtered according to the node report of successful transmission generated by the One simulator. The node contact report generated by another One simulator was used to calculate the data of the three feature vectors required for training the model. The feature vectors and the high-quality node data were then fed into the model to train the random forest model, which was then able to identify high-quality nodes. The simulation experiment was carried out in the ONE simulator in the Helsinki city centre, with two categories of weekday and holiday scenarios, each with a different number of nodes. Three groups were set up in each category: the original unmodified group, the group with high-quality nodes, and the group with random nodes. The results show that this method of loading high-quality nodes significantly improves the performance of the protocol, increasing the success rate of information transmission and reducing latency. This study not only confirms the feasibility of using advanced machine learning techniques to improve DTN routing protocols, but also lays the foundation for future innovations in emergency communication network management.

翻译：本研究旨在优化延迟容忍网络中的"喷洒与等待"协议，以提升紧急情况下（特别是交通事故场景）信息传输性能。由于延迟容忍网络具有间歇性连接和动态环境特性，传统路由协议往往无法有效工作。本研究采用名为随机森林的机器学习方法来识别"高质量"节点。"高质量"节点指具有高消息投递成功率和最优路径的节点。高质量节点数据根据ONE模拟器生成的传输成功节点报告进行筛选，另一ONE模拟器生成的节点接触报告则用于计算训练模型所需的三个特征向量数据。将特征向量与高质量节点数据输入模型后，训练出的随机森林模型即能识别高质量节点。仿真实验在赫尔辛基市中心的ONE模拟器中进行，设置工作日与节假日两类场景，每类场景包含不同节点数量。每个类别设置三组对比：原始未修改组、高质量节点组和随机节点组。结果表明，加载高质量节点的方法显著提升了协议性能，提高了信息传输成功率并降低了延迟。本研究不仅证实了利用先进机器学习技术改进延迟容忍网络路由协议的可行性，还为未来应急通信网络管理的创新奠定了基础。