Evaluation of Caching Strategies Based on Access Statistics of Past Requests

  • Gerhard Hasslinger
  • Konstantinos Ntougias
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8376)


Delivery of popular content on the Internet usually does not rely on a single server but is supported by content delivery networks (CDNs) that reactively store requested content in distributed cache servers. CDNs strengthen the availability and downloading throughput. Moreover, they shorten transport paths when caches in the proximity of requesting users are preferred.

We study how the cache hit rate as the main efficiency criterion of web caches depends on the request statistics and the caching strategy that selects which content should be placed in or evicted from a cache. Although the least recently used (LRU) strategy seems to be widely deployed in web caches, our comparison in simulations and analytic case studies reveals essentially higher hit rates for alternatives based on the complete request statistics in the past under the realistic assumption of Zipf distributed user requests.


Web caching replacement strategies least recently used (LRU) least frequently used (LFU) sliding window geometric fading cache hit rate analysis and simulation Zipf distributed requests 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Akamai, State of the Internet, Quarterly Report Series (2013),
  2. 2.
    Bahat, O., Makowski, M.: Optimal replacement policies for non-uniform cache objects with optional eviction. In: Proc. IEEE Infocom Conference, San Francisco, CA, USA (2003)Google Scholar
  3. 3.
    Bolla, R., et al.: Modeling file popularity in peer-to-peer file sharing systems. In: Proc. 14th ASMTA Conf., Prague, Czech Republic, pp. 149–155 (2007)Google Scholar
  4. 4.
    Braun, L., et al.: Analyzing caching benefits for YouTube traffic in edge networks: A measurement-based evaluation. In: IEEE Network Operations & Management Symposium, Maui, Hawaii, USA (2012)Google Scholar
  5. 5.
    Breslau, L., et al.: Web caching and Zipf-like distributions: Evidence and implications. In: Proc. IEEE Infocom (1999)Google Scholar
  6. 6.
    Buyya, R., Pathan, M., Vakali, A. (eds.): Content delivery networks. LNEE, vol. 9. Springer, Heidelberg (2008)Google Scholar
  7. 7.
    Cao, P., Irani, S.: Cost aware WWW caching algorithms. In: Proc. USENIX Symposium, Monterey, CA, USA (1997)Google Scholar
  8. 8.
    Cha, M., et al.: I tube, you tube, everybody tubes: Analyzing the world’s largest user generated content video system. In: Internet Measurement Conference, IMC 2007, San Diego, USA (2007)Google Scholar
  9. 9.
    Che, H., Tung, Y., Wang, Z.: Hierarchical web caching systems: modeling, design and experimental results. IEEE JSAC 20(7), 1305–1314 (2002)Google Scholar
  10. 10.
    Charzinski, J.: Traffic properties, client side cachability and CDN usage of popular web sites. In: Müller-Clostermann, B., Echtle, K., Rathgeb, E.P. (eds.) MMB & DFT 2010. LNCS, vol. 5987, pp. 136–150. Springer, Heidelberg (2010)Google Scholar
  11. 11.
    Cohen, B.: Incentives build robustness in BitTorrent (2003),
  12. 12.
    Dan, A., Towsely, D.: An approximate analysis of the LRU and FIFO buffer replacement schemes. SIGMETRICS Perform. Eval. Rev. 18, 143–152 (1990)CrossRefGoogle Scholar
  13. 13.
    Fielding, R., et al.: Hypertext transfer protocol HTTP/1.1: Caching, Internet-Draft, work in progr. (2013),
  14. 14.
    Fricker, C., Robert, P., Roberts, J.: A versatile and accurate approximation for LRU cache performance. In: Proc. 24th International Teletraffic Congress, Kraków, Poland (2012)Google Scholar
  15. 15.
    Fricker, C., et al.: Impact of traffic mix on caching performance in a content-centric network. In: IEEE INFOCOM 2012 Workshops, pp. 310–315 (2012)Google Scholar
  16. 16.
    Gill, P., et al.: YouTube traffic characterization: A view from the edge. In: Internet Measurement Conference, IMC 2007, San Diego, USA (2007)Google Scholar
  17. 17.
    Guo, L., et al.: Does Internet media traffic really follow Zipf-like distributions? In: ACM SIGMETRICS (2007)Google Scholar
  18. 18.
    Hasslinger, G., Hohlfeld, O.: Efficiency of caches for content distribution on the Internet. In: Proc. 22nd International Teletraffic Congress, Amsterdam, The Netherlands (2010)Google Scholar
  19. 19.
    Hasslinger, G., Hartleb, F., Beckhaus, T.: User access to popular data on the internet and approaches for IP traffic flow optimization. In: Al-Begain, K., Fiems, D., Horváth, G. (eds.) ASMTA 2009. LNCS, vol. 5513, pp. 42–55. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  20. 20.
    Hasslinger, G., Hartleb, F.: Content delivery and caching from a network provider’s perspective. Special Issue on Internet based Content Delivery, Computer Networks 55, 3991–4006 (2011)Google Scholar
  21. 21.
    Kandavanam, G., Botvich, D., Balasubranmaniam, S.: PaCRA: A path-aware content replication approach to support QoS guaranteed video on demand service in metropolitan IPTV networks. In: IEEE/IFIP Network Operations & Mgnt. Symp. NOMS, pp. 591–598 (2010)Google Scholar
  22. 22.
    Karakostas, G., Serpanos, D.N.: Exploitation of different types of localities for web caching. In: Proc. 7th IEEE Symposium on Computers and Communications (ISCC), pp. 207–212 (2002)Google Scholar
  23. 23.
    Lee, D., et al.: LRFU: A spectrum of policies that subsumes the least recently used and least frequently used policies. IEEE Transactions on Computers 50(12), 1352–1361 (2001)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Megiddo, N., Modha, S.: Outperforming LRU with an adaptive replacement cache algorithm. IEEE Computer 37(4), 4–11 (2004)CrossRefGoogle Scholar
  25. 25.
    Panchekha, P.: Caching in theory and practice, Dropbox TechBlog (2012),
  26. 26.
    Podlipnik, S., Böszörmenyi, L.: A survey of web cache replacement strategies. ACM Computer Surveys, 374–398 (2003)Google Scholar
  27. 27.
    Rabinovich, M., Spatscheck, O.: Web caching and replication. Addison-Wesley, Boston (2002)Google Scholar
  28. 28.
    Reed, W.J.: The Pareto, Zipf and other power laws. Economics Letters 74(1), 15–19 (2001)CrossRefGoogle Scholar
  29. 29.
    Shah, K., Mitra, A., Matani, D.: An O(1) algorithm for implementing the LFU cache eviction scheme accessible from, or (2010)
  30. 30.
    Vakali, A.I.: LRU-based algorithms for web cache replacement. In: Bauknecht, K., Madria, S.K., Pernul, G. (eds.) EC-Web 2000. LNCS, vol. 1875, pp. 409–418. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  31. 31.
    Wessels, D.: Squid: The definitive guide. O’Reilly (2004)Google Scholar
  32. 32.
    Williams, A., et al.: Web workload characterization: Ten years later. In: Tang, X., et al. (eds.) Web Content Delivery, pp. 3–21. Springer (2005)Google Scholar
  33. 33.
    Zhao, S., Stutzbach, D., Rejaie, R.: Characterizing files in the modern Gnutella network: A measurement study. SPIE/ACM Proc. Multimedia Computing and Networking (2006)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Gerhard Hasslinger
    • 1
  • Konstantinos Ntougias
    • 1
  1. 1.Deutsche Telekom TechnikFixed Mobile EngineeringDarmstadtGermany

Personalised recommendations