Novel Web Proxy Cache Replacement Algorithms using Machine Learning Techniques for Performance Enhancement

A web cache is a mechanism for the temporary storage (caching) of web documents, such as HTML pages and images, to reduce bandwidth usage, server load, and perceived lag. A web cache stores copies of documents passing through it; subsequent requests may be satisfied from the cache if certain conditions are met. In this paper, machine learning techniques are used to increase the performances of traditional Web proxy caching policies such as SIZE, and Hybrid. Naïve Bayes (NB) and decision tree (C4.5) are used and integrated with traditional Web proxy caching techniques to form better caching approaches known as NB–SIZE, and C4.5–Hybrid. The proposed approaches are evaluated by trace-driven simulation and compared with traditional Web proxy caching techniques. Experimental results have revealed that the proposed NB–SIZE and C4.5–Hybrid significantly increased Pure Hit-Ratio, Byte Hit-Ratio and to reduced the latency when compared with SIZE and Hybrid