Forecasted Popularity Based Lazy Caching Strategy


The KIPS Transactions:PartA, Vol. 10, No. 3, pp. 261-268, Aug. 2003
10.3745/KIPSTA.2003.10.3.261,   PDF Download:

Abstract

In this paper, we propose a new caching strategy for web servers. The proposed strategy collects only the statistics of the requested file, for example the popularity, when a request arrives. At a point of time, only files with higher forecasted popularity are cached all together. Forecasted popularity based lazy caching (FPLC) strategy uses exponential smoothing method for forecast popularity of web files. And, FPLC strategy shows that the cache hit ratio and the cache transfer ratio are better than those produced by other caching strategy. Furthermore, the experiment that is performed with real log files built from web servers shows our study on forecast method for popularity of web files improves cache efficiency.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
P. Cheol and Y. H. Yeong, "Forecasted Popularity Based Lazy Caching Strategy," The KIPS Transactions:PartA, vol. 10, no. 3, pp. 261-268, 2003. DOI: 10.3745/KIPSTA.2003.10.3.261.

[ACM Style]
Park Cheol and Yu Hae Yeong. 2003. Forecasted Popularity Based Lazy Caching Strategy. The KIPS Transactions:PartA, 10, 3, (2003), 261-268. DOI: 10.3745/KIPSTA.2003.10.3.261.