计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (13): 103-106.DOI: 10.3778/j.issn.1002-8331.2009.13.031

• 网络、通信、安全 • 上一篇    下一篇

基于访问量预测的教育资源网格副本放置策略

邹立达,刘方爱,马 艳   

  1. 山东师范大学 信息科学与工程学院,济南 250014
  • 收稿日期:2008-03-06 修回日期:2008-06-12 出版日期:2009-05-01 发布日期:2009-05-01
  • 通讯作者: 邹立达

Forecast of access traffic based education resource grid replication strategy

ZOU Li-da,LIU Fang-ai,MA Yan   

  1. School of Information Science and Engineering,Shandong Normal University,Jinan 250014,China
  • Received:2008-03-06 Revised:2008-06-12 Online:2009-05-01 Published:2009-05-01
  • Contact: ZOU Li-da

摘要: 副本放置策略是数据网格副本机制的关键问题。针对教育资源网格环境,提出了基于访问量预测的副本放置策略(FATBRS),并介绍了基于历史数据的访问量预测(FATTHD)和基于人工神经网络的访问量预测(FATANN)两种访问量预测方法。FATBRS策略有效降低了用户的访问延迟,仿真实验证实了该策略性能的优越性。

关键词: 副本放置, 教育资源网格, 访问量, 人工神经网络

Abstract: Grid replication strategy is the key problem of replica mechanism.The forecast of access traffic based education resource grid replication strategy(FATBRS) is presented for education resource grid.Two methods of forecasting accessing traffic are introduced,which are the forecast of access traffic based on historical data(FATTHD) and the forecast of access traffic based on artificial neural networks(FATANN).FATBRS reduces the access delay efficiently and it is proved through the analysis of experiments.

Key words: replica allocation, education resource grid, access traffic, artificial neural networks