2nd International ICST Conference on Scalable Information Systems

Research Article

An Evolution-Based Cache Scheme for Scalable Mobile Data Access

Download517 downloads
  • @INPROCEEDINGS{10.4108/infoscale.2007.194,
        author={Fan Ye and Qing Li and Enhong Chen},
        title={An Evolution-Based Cache Scheme for Scalable Mobile Data Access},
        proceedings={2nd International ICST Conference on Scalable Information Systems},
        proceedings_a={INFOSCALE},
        year={2010},
        month={5},
        keywords={Stream Media Caching Hybrid Scalable Caching Scheme Evolutionary Algorithm},
        doi={10.4108/infoscale.2007.194}
    }
    
  • Fan Ye
    Qing Li
    Enhong Chen
    Year: 2010
    An Evolution-Based Cache Scheme for Scalable Mobile Data Access
    INFOSCALE
    ICST
    DOI: 10.4108/infoscale.2007.194
Fan Ye1,2,3,*, Qing Li2,3,*, Enhong Chen1,2,*
  • 1: Department of Computer Science and Technology, University of Science & Technology of China, Hefei, China.
  • 2: Joint Research Lab of Excellence, CityU-USTC Advanced Research Institute, Suzhou, China.
  • 3: Department of Computer Science, City University of Hong Kong, Hong Kong, China.
*Contact email: yfan@mail.ustc.edu.cn, itqli@cityu.edu.hk, cheneh@ustc.edu.cn

Abstract

Streaming media data access has been a problem for several years, and the problem becomes tougher in the mobile environment in which mobile users use mobile devices that are of rather limited storage space, preventing the clients from having a large cache. In this paper, we design a novel evolutionary caching algorithm for base stations to adapt to the user requests, so as to make the scheme more adaptive to the changing environment while maintaining good Byte Hit Ratio (BHR) or Number Hit Ratio (NHR) for the real world requests. We evaluate the effectiveness of our evolutionary caching algorithm through simulation studies, the results of which demonstrate that our scheme can obtain good performance on buffering streaming media data for user requests as far as the BHR and NHR metrics are concerned.