Replacement algorithm based on page size and LRU algorithm

Dissertant

al-Amush, Shifa Muhammad

Thesis advisor

al-Rababiah, Mamun
Zabyan, Arwa

Comitee Members

Samawi, Venus W.
Samarah, Samir
Shatnawi, Umar

University

Al albayt University

Faculty

Prince Hussein Bin Abdullah Faculty for Information Technology

Department

Department of Computer Science

University Country

Jordan

Degree

Master

Degree Date

2013

English Abstract

Web caching is a technique used to reduce the load on the server and has the role to cache the most requested document from the client.

In this thesis we propose a novel replacement algorithm, SLRU (Size Based- Least Recently Used) that adds a parameter to the LRU (Least Recently Used) is the size of document.

The proposed SLRU algorithm improves the replacement mechanism that improves the cache performance.

Our goal is to increase the hit rate and decrease the miss rate in term of cached web page’s size.

If the cache has many large web pages that haven’t used for a lot of time, such web pages are victim to evict from the cache to make room for other smaller web pages more requested.

SLRU algorithm evicts the web page with size larger than the new web page and with the least reference which means this victim web page is not requested by the user for a long of time. A comprehensive comparison is made between SLRU and LRU algorithm.

Experimental results show that the SLRU significantly reduces the number of cache misses in comparison with LRU.

Simulation results show, that SLRU algorithm can provide a maximum value of approximately 8.19% improvement in the miss ratio over LRU algorithm in data cache.

And approximately 4.12% improvement in hit ratio in data cache.

This improvement is attributed to the fact that our algorithm provides an importance to the web page size ( that may not be deleted according to LRU’s rules).

Main Subjects

Mathematics

No. of Pages

45

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-416180