Data Mining and Knowledge Engineering

Vipul Dholariya ¹, Madhu Shukla ¹

Affiliations
1 Marwadi Education Foundation Group of Institutions, Rajkot, IN

Abstract

Due to the huge amount of internet users it's create heavy network traffic, require high bandwidth and low latency period. Web Caching is the important technique to reach high performance and to increase the efficiency of browser. The object takes to much less time fetch from cache memory compare to original server. This paper gives a Recency Frequency Time based Policy over the traditional policy which has better performance, low overhead and is simple to implement and simulate. Simulations show that our algorithm performs better than Least-Recently-Used (LRU), WRP (Weighting and Ranking Policy).

Keywords

LRU, WRP, Latency Period, Low Overhead.

Full Text

     

Vipul Dholariya ¹, Madhu Shukla ²

Affiliations
1 Marwadi Education Foundation Group of Institute, Gujarat Technological University, Ahmedabad, Gujarat, IN
2 RK University, Rajkot, IN

Abstract

Day by Day increasing the human activity on internet, operating systems and databases, which create heavy network traffic. One of the measurable step in system designing is caching. It helps to get higher performance in various fields like databases, operating systems and World Wide Web. System performance differs according to various caching policies. Hit-ratio is one of the important factors in cache replacement policy. In caching systems, a replacement policy is necessary for determining when and what to evict from the cache. We discuss in this article about LRU, LFU, FIFO, CAR, OPTIMAL, WRP and AWRP algorithms.

Keywords

Cache Replacement Policy, Weighting and Ranking Policy, Hit-Miss, Amortize Time.

Full Text