基于神经网络的铁路通信网络传输延迟控制方法  

Transmission Delay Control Method of Railway Communication Networks Based on Neural Network

作　　者：董玉圻 Dong Yuqi(Equipment Technology Center,National Railway Administration of the People's Republic of China,Beijing 100702,China)

机构地区：[1]国家铁路局装备技术中心,北京100702

出　　处：《铁路通信信号工程技术》2023年第1期33-39,共7页Railway Signalling & Communication Engineering

摘　　要：研究一种基于神经网络的铁路通信网络传输延迟控制方法。利用TCN网络分析仪抓取的通信网络延迟数据,组成数据样本。以数据样本为输入,利用神经网络实现铁路通信网络传输延迟预测。以预测结果为输出,结合PID,得出延迟控制量和延迟补偿量,实现铁路通信网络传输延迟控制。结果表明,与基于功率控制协议的控制方法、基于延迟补偿的控制方法相比,在新的控制方法应用下,延迟时间更短,通信链路速率更高,由此证明新研究的控制方法的有效性。A transmission delay control method of railway communication networks based on a neural network is studied.This study uses the communication network delay data captured by TCN network analyzer to serve as data samples.With the data samples as input,the prediction of transmission delays of railway communication networks is realized by using the neural network.With the prediction results as the output,combined with PID,the delay control quantity and delay compensation quantity are obtained to realize the transmission delay control of railway communication networks.The results show that the new control method in this paper reduces the delay time and increases the communication link rate as compared with the control method based on power control protocol and the control method based on delay compensation,which proves the effectiveness of this new method.

关 键 词：神经网络 铁路通信网络 延迟预测 传输延迟 延迟控制 

分 类 号：U285.5[交通运输工程—交通信息工程及控制]