您的位置:首页  > 论文页面

UDP、FTP日流量的对数正态分布模型

发表时间:2019-12-31  浏览量:909  下载量:125
全部作者: 董颖,李明
作者单位: 华东师范大学通信与电子工程学院
摘 要: 以日本MAWI工作组(MAWI Working Group Traffic Archive)的网络日流量数据作为研究对象,分析了2007年和2018年中的用户数据报协议(user datagram protocol,UDP)、文件传输协议(file transfer protocol,FTP)网络日流量数据的分布特性,得到分布函数。计算理论分布和原始曲线的均方误差,并将此作为衡量拟合的标准。研究结果表明,UDP、FTP网络日流量数据均具有重尾分布特性,经过分析和计算发现实际数据可以用对数正态分布进行拟合。均方误差均达到标准,证明了数据分析和预测的准确度。
关 键 词: 通信技术;网络日流量建模;重尾分布;对数正态分布
Title: Lognormal distribution model of UDP and FTP daily traffic
Author: DONG Ying, LI Ming
Organization: School of Communication and Electronic Engineering, East China Normal University
Abstract: The network daily traffic data of the MAWI Working Group Traffic Archive in Japan is taken as the research object in this paper, and the distribution characteristics of network daily traffic data in user datagram protocol (UDP) and file transfer protocol (FTP) in 2007 and 2018 are analyzed. And the distribution function is obtained. The mean square error of the theoretical distribution and the original curve is calculated, which is used as a measure of the fit. The research results show that the network daily traffic data of UDP and FTP all have heavy-tailed distribution characteristics. After analysis and calculation, it is found that the actual data can be fitted with a lognormal distribution. The mean square error is up to standard, it indicates the accuracy of data analysis and prediction.
Key words: communications technology; network daily traffic modeling; heavy-tailed distribution; lognormal distribution
发表期数: 2019年12月第6期
引用格式: 董颖,李明. UDP、FTP日流量的对数正态分布模型[J]. 中国科技论文在线精品论文,2019,12(6):994-999.
 
4 评论数 0
暂无评论
友情链接