A Caching Strategy Considering Data Popularity in Pull-Based Data Broadcast Systems

풀 기반 데이타 방송 시스템에서의 데이타 인기도를 고려한 캐싱 전략

  • 신동천 (중앙대학교 정보시스템학과)
  • Published : 2006.08.01

Abstract

A caching is a useful technique to alleviate performance degradation due to the inherent narrow bandwidth by reducing contention of broadcast requests. In this paper, we propose a caching strategy for pull-based data broadcast system which considers data popularity among clients. In addition, the proposed strategy also reflects recentness of data access based on data broadcast version. Then, we evaluate the performance of proposed strategy through a simulation approach. According to the results, the strategy considering both hit ratio and miss cost shows better performance than the traditional LRU. In addition, the strategy considering data popularity among clients shows better performance in some cases.

캐싱은 데이타 방송 시스템에서 방송 요청의 경쟁을 줄임으로써 좁은 대역폭으로 인한 시스템 성능의 저하를 완화할 수 있는 유용한 방법이다. 본 논문에서는, 풀 기반 방송 시스템에서 클라이언트들간의 데이타 인기도를 반영하는 캐싱 전략을 제안한다. 아울러, 데이타 방송 버전을 이용하여 데이타 접근의 최근성을 반영할 수 있도록 하고 제안한 전략의 성능을 시뮬레이션을 통하여 평가한다. 성능 평가에 따르면, 히트율과 미스 비용을 함께 고려한 전략이 전통적 전략인 LRU 보다 성능 우위를 보이고 있다. 클라이언트들의 데이타 인기도를 고려한 전략은 일부 경우에 있어 성능 우위를 보여 주고 있다.

Keywords

References

  1. D. Barbara, 'Mobile Computing and Databases-A Survey:' IEEE Transactions on Knowledge Engineering, Vol. 11, No, 1, pp. 108-117, J999 https://doi.org/10.1109/69.755619
  2. S. K. Madria and B. K. Bhargava, 'A Transaction Model to Improve Data Availability in Mobile Computing,' Journal of Distributed and Parallel Databases, Vol. 10, No. 2, pp, 127-160, 2001 https://doi.org/10.1023/A:1019232412740
  3. S. Acharya, M. Franklin, and S. Zdonik, 'Balancing Push and Pull for Data Broadcast,' Proc. of ACM SIGMOD, pp, 183-194, 1997 https://doi.org/10.1145/253262.253293
  4. T. Choi, Y. Kim, K. Chung, 'A Prefetching Scheme based on the Analysis of User Access Patterns in News-On-Demand System,' Proc. of ACM Int. Conf. on Multimedia, pp. 145-148, 1999 https://doi.org/10.1145/319463.319482
  5. C. Griwodz, M. Bar, L. C. Wolf, 'Long-term movie popularity models in video-on-demand systems: or the life of an on-demand movie,' Proc. of ACM Int. Conf. on Multimedia, pp. 349-357, 1997 https://doi.org/10.1145/266180.266386
  6. K. Y. Lai, Z. Tari, and P. Bertok, 'Cost Efficient Broadcast based Cache Invalidation for Mobile Environments,' Proc. of ACM Symposium on Applied Computing, pp. 871-877, 2003 https://doi.org/10.1145/952532.952705
  7. X. Shao and Y. Lu, 'Maintain Cache Consistency of Mobile Database Using Dynamical Periodical Broadcast Strategy,' Proc of Int. Conf. on Machine Learning and Cybernetics, pp. 2389-2393, 2003 https://doi.org/10.1109/ICMLC.2003.1259910
  8. S. Galvin and P. B. Galvin, Operation System Concepts, 4th Edition, Addison Wesley, 1994
  9. S. Khanna and V. Liberatore, 'On Broadcast Disk Paging,' Proc. of ACM Symposium on the Theory of Computing, pp. 634-643, 1998 https://doi.org/10.1145/276698.276879
  10. Y. J. Lee and D. C. Shin, 'Performance of Caching Strategies for Pull-based Data Broadcast Systems in Mobile Computing Environments,' Journal of Computer Information Systems, Vol. 15, No. 4, pp. 102-115, 2005
  11. V. Liberatore, 'Caching and Scheduling for Broadcast Disk Systems,' Technical Report 98-71, UMIACS, 1998
  12. J. Xu, Q., Hu, W.-C. Lee, and D. L. Lee. 'Performance Evaluation of Optimal Cache Replacement Policy for Wireless Data Dissemination,' IEEE Transactions on Knowledge and Data Engineering, Vol. 16, No. 1, pp. 125-139, 2004 https://doi.org/10.1109/TKDE.2004.1264827
  13. D. Aksoy and M. Franklin, 'RxW: A Scheduling Approach for Large-Scale Data Broadcast,' IEEE/ACM Transactions on Networking, Vol. 7, No.6, pp. 846-860, 1999 https://doi.org/10.1109/90.811450
  14. H. Schwetman, CSIM User's Guide for Use with CSIM Revision 16, Microelectronics and Computer Technology Corporation, 1992