Intelligent Web proxy caching approaches based on machine learning techniques

In this paper, machine learning techniques are used to enhance the performances of conventional Web proxy caching policies such as Least-Recently-Used (LRU), Greedy-Dual-Size (GDS) and Greedy-Dual-Size-Frequency (GDSF). A support vector machine (SVM) and a decision tree (C4.5) are intelligently incorporated with conventional Web proxy caching techniques to form intelligent caching approaches known as SVM–LRU, SVM–GDSF and C4.5–GDS. The proposed intelligent approaches are evaluated by trace-driven simulation and compared with the most relevant Web proxy caching polices. Experimental results have revealed that the proposed SVM–LRU, SVM–GDSF and C4.5–GDS significantly improve the performances of LRU, GDSF and GDS respectively.

► Support vector machine (SVM) and decision tree (C4.5) are trained from logs file. ► SVM and C4.5 achieve much better accuracy and faster than other algorithms. ► SVM and C4.5 are effectively utilized to give intelligent proxy caching approaches. ► The intelligent approaches significantly improve the Web proxy caching performance.