基于时变泊松模型的WWW流量贝叶斯预测
网络与互联网体系结构
2009-12-03 v4 机器学习
摘要
利用过去观测到的流量数据以较小的计算复杂度进行流量预测是服务器和网络规划的重要问题之一。本文以万维网(WWW)流量作为基础研究，从统计决策理论的角度，探讨基于时变泊松模型的网络流量贝叶斯预测。在该模型下，我们将证明估计的预测值可以通过简单的算术计算得到，并且从理论和实证两个角度都能很好地表达真实的WWW流量。
引用
@article{arxiv.0906.3923,
title = {Bayesian Forecasting of WWW Traffic on the Time Varying Poisson Model},
author = {Daiki Koizumi and Toshiyasu Matsushima and Shigeichi Hirasawa},
journal= {arXiv preprint arXiv:0906.3923},
year = {2009}
}
备注
8 pages, 6 figures. This paper was published in Proceeding of The 2009 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'09) in July, 2009. In version of v4, research grants are included in acknowledgment