华南理工大学学报(自然科学版) ›› 2011, Vol. 39 ›› Issue (7): 127-133.doi: 10.3969/j.issn.1000-565X.2011.07.021

• 计算机科学与技术 • 上一篇    下一篇

使用MSS 维护语义缓存一致性的方法

梁茹冰1,2 刘琼1†   

  1. 1.华南理工大学 计算机科学与工程学院,广东 广州 510006; 2.华南农业大学 理学院,广东 广州 510642
  • 收稿日期:2010-11-03 修回日期:2011-03-30 出版日期:2011-07-25 发布日期:2011-06-03
  • 通信作者: 刘琼(1959-) ,女,教授,博士生导师,主要从事计算机网络研究. E-mail: liuqiong@scut.edu.cn E-mail:liang_ru_bing@163.com
  • 作者简介:梁茹冰(1980-) ,女,在职博士生,华南农业大学讲师,主要从事语义缓存、移动计算研究.
  • 基金资助:

    国家“973”计划项目( 2007CB07100, 2007CB07106)

Maintenance of Semantic Cache Consistency via Mobile Support Station

Liang Ru-bing1,2  Liu Qiong1   

  1. 1. School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,Guangdong,China; 2. College of Science,South China Agricultural University,Guangzhou 510642,Guangdong,China
  • Received:2010-11-03 Revised:2011-03-30 Online:2011-07-25 Published:2011-06-03
  • Contact: 刘琼(1959-) ,女,教授,博士生导师,主要从事计算机网络研究. E-mail: liuqiong@scut.edu.cn E-mail:liang_ru_bing@163.com
  • About author:梁茹冰(1980-) ,女,在职博士生,华南农业大学讲师,主要从事语义缓存、移动计算研究.
  • Supported by:

    国家“973”计划项目( 2007CB07100, 2007CB07106)

摘要: 传统语义缓存一致性维护算法中存在失效报告空间复杂度高和通信开销大的问题,而目前的研究多只关注客户方算法的改善,不能从根本上解决这些问题.为此,文中提出了基于3 层缓存结构的、用移动支持站点协助客户方进行缓存一致性维护的方法.通过建立索引表并运用比特序列方法形成失效报告,以达到进一步压缩报告长度的效果; 使用队列存储更新序列对更新粒度进行细化及简化客户方缓存维护过程,从而节省网络带宽,支持频繁断接下的缓存一致性维护.仿真结果表明,该算法较其它算法明显减少了失效报告长度和一致性维护的网络通信开销.

关键词: 移动计算, 移动支持站点, 语义缓存, 失效报告, 粒度细化

Abstract:

The traditional algorithms of semantic cache consistency maintenance are of enormous data communication cost and space complexity of invalidation report. However,most of the current researches mainly focus on the client's algorithms and are unable to solve the above-mentioned problems radically. In this paper,a novel method of semantic cache consistency maintenance with a three-layer cache structure is proposed,which uses the mobile support station ( MSS) to store mobile client's semantic cache items. Then,the corresponding index table is presented and an invalidation report is created based on the bit sequence to further shorten the report length. Finally,the updating sequence is stored in a queue and is used to refine the updated granularity and simplify the consistency maintenance from clients,thus saving the network bandwidth and supporting the cache consistency maintenance in the condition of frequent network disconnection. Simulated results show that the proposed algorithm remarkably reduces the invalidation report size and saves the data communication cost for consistency maintenance.

Key words: mobile computing, mobile support station, semantic cache, invalidation report, granularity refining