估计船舶通信网络流量，可以更好地了解网络性能，有助于优化网络配置，提高船舶通信网络的性能和可靠性，确保船舶航行过程中的通信畅通。为此，设计基于大数据统计的船舶通信网络流量估计数学模型，以提升网络流量估计效果。利用C-C算法计算船舶通信网络流量的延迟时间，通过G-P算法计算船舶通信网络流量的嵌入维数；依据延迟时间与嵌入维数，转换原始船舶通信网络流量时间序列数据，得到多维船舶通信网络流量时间序列数据；利用Map机制为各节点上的极限学习机分配数据子集，建立船舶通信网络流量估计数学模型；通过Reduce机制，汇总全部网络流量估计数学模型，得到最终的网络流量估计结果。实验证明，该模型可有效确定延时时间与嵌入维数，分别为5 min与6维；该模型可精准估计船舶通信网络流量。
Estimating the traffic of ship communication network can better understand the network performance, help to optimize the network configuration, improve the performance and reliability of ship communication network, and ensure the smooth communication during ship navigation. Therefore, a mathematical model of ship communication network traffic estimation based on big data statistics is designed to improve the effect of network traffic estimation. C-C algorithm is used to calculate the delay time of ship communication network traffic, and G-P algorithm is used to calculate the embedded dimension of ship communication network traffic. According to the delay time and embedded dimension, the original ship communication network traffic time series data is converted to obtain the multi-dimensional ship communication network traffic time series data. Map mechanism is used to assign data subset to the extreme learning machine on each node, and the mathematical model of ship communication network traffic estimation is established. The reduce mechanism is used to summarize all the mathematical models of network traffic estimation and get the final network traffic estimation result. Experimental results show that the model can effectively determine the delay time and embedding dimension, which are 5 min and 6D respectively. This model can accurately estimate the traffic of ship communication network.
2024,46(6): 169-172 收稿日期：2023-06-27
DOI：10.3404/j.issn.1672-7649.2024.06.030
分类号：TP391
基金项目：广西职业教育教学改革重点项目（GXGZJG2021A035）
作者简介：宁滔(1978-),男,硕士,高级工程师,研究方向为云计算及大数据、数据挖掘、信息可视化和网络安全等
参考文献：
[1] 刘敬贤, 高广旭, 刘奕, 等. 基于卷积神经网络及长短时记忆网络的短时船舶交通流量预测[J]. 中国航海, 2022, 45(2): 56-61+68.
LIU Jing-xian, GAO Guang-xu, LIU Yi, et al. Short-term water traffic flow prediction with convolutional neural network and long short-term memory network[J]. Navigation of China, 2022, 45(2): 56-61+68.
[2] 杨家轩, 许洲锦, 来源, 等. 基于概率攻击图的船舶网络安全评估模型[J]. 大连海事大学学报, 2023, 49(1): 26-33.
YANG Jia-xuan, XU Zhou-jin, LAI Yuan, et al. Ship cyber security assessment model based on probability attack graph[J]. Journal of Dalian Maritime University, 2023, 49(1): 26-33.
[3] 高勇, 陆钱春, 李锋. 面向IP网络扩容应用的复杂网络流量预测方法[J]. 电信科学, 2023, 39(9): 21-31.
GAO Yong, LU Qian-chun, LI Feng. A complex network traffic prediction method for IP network expansion applications[J]. Telecommunications Science, 2023, 39(9): 21-31.
[4] 徐海兵, 郭久明. 基于双向GRU模型的网络流量预测的研究[J]. 电子技术应用, 2022, 48(2): 19-22+27.
XU Hai-bing, GUO Jiu-ming. Research on network traffic prediction based on Bi-GRU model[J]. Application of Electronic Technique, 2022, 48(2): 19-22+27.
[5] 薛自杰, 卢昱妃, 宁芊, 等. 基于时空特征融合的网络流量预测模型[J]. 哈尔滨工业大学学报, 2023, 55(5): 30-38.
XUE Zi-jie, LU Yu-fei, NING Qian, et al. Network flow prediction based on spatial-temporal features fusion[J]. Journal of Harbin Institute of Technology, 2023, 55(5): 30-38.
