A new approach for a proxy-level web caching mechanism

In this study we propose a new proxy-level web caching mechanism that takes into account aggregate patterns observed in user object requests. Our integrated caching mechanism consists of a quasi-static portion that exploits historical request patterns, as well as a dynamic portion that handles deviations from normal usage patterns. This approach is more comprehensive than existing mechanisms because it captures both the static and the dynamic dimensions of user web requests. The performance of our mechanism is empirically tested against the popular least recently used (LRU) caching policy using an actual proxy trace dataset. The results demonstrate that our mechanism performs favorably versus LRU. Our caching approach should be beneficial for computer network administrators to significantly reduce web user delays due to increasing traffic on the Internet. (c) 2008 Elsevier B.V. All rights reserved.