WEB PROXY CACHE REPLACEMENT POLICIES USING NAÏVE BAYES (NB) MACHINE LEARNING TECHNIQUE FOR ENHANCED PERFORMANCE OF WEB PROXY

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 the copies of documents passing through it and any subsequent requests may be satisfied from the cache if certain conditions are met. In this paper, Naïve Bayes (NB) a machine learning technique has been used to increase the performance of traditional Web proxy caching policies such as SIZE, and Hybrid. Naïve Bayes (NB) is used and integrated with traditional Web proxy caching techniques to form better caching approaches known as NB–SIZE and NB–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 NB–Hybrid significantly increased Pure Hit-Ratio, Byte Hit-Ratio and reduced the latency when compared with SIZE and Hybrid