
浏览全部资源
扫码关注微信
1. 北京交通大学电子信息工程学院
2. 上海微创软件有限公司
3. 南京理工大学计算机科学与技术系,北京,100044
4. ,江苏,南京,210094
纸质出版日期:2005
移动端阅览
张冰怡, 边裕兰, 张宏科, 等. 网络通信量模型的线性鉴别分析[J]. 通信学报, 2005,(11).
ZHANG Bing-yi, BIAN Yu-lan, ZHANG Hong-ke, et al. Linear discriminant analysis in network traffic modeling[J]. 2005, (11).
判断网络通信量模型与真实数据拟合度的常用方法是Hurst参数比较法、数据直方图比较法和自相关函数比较法。其中Hurst参数法计算结果不准确
不能给出正确判断
而后两者只能主观给出一个定性判断。基于线性鉴别分析原理
给出了一个拟合度判断算法。用该算法分析了不同差别程度的模型仿真数据和大量NS仿真数据
应用效果显著
与常用方法相比
能定量、准确地判断网络通信量模型的拟合度。
It was not easy to give an accurate judgment of whether the traffic model fitting the actual traffic. The common method was to compare the Hurst parameter
data histogram and autocorrelation function. The method of comparing Hurst parameter could’t give exact results and judgment. The method of comparing data histogram and autocorrelation could only give a qualitative judgment. Based on linear discriminant analysis a arithmetic was proposed. Utilizing this arithmetic the data in the sets of different traffic model and in NS was analyzed. The results are accurate. Compared with traditional method this arithmetic is useful and can conveniently give an accurate judgment for complex network traffic trace.
0
浏览量
115
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621