An HTTP web traffic model based on the top one million visited web pages

Abstract

The ever-changing behavior of HTTP web pages requires an adjustment of the web models used for simulation and benchmarking. In this paper, we present the statistical data of the one million most visited web sites. Using this data, we examine the changes in size and number of objects by comparing our findings with well-known web traffic models. The results show a trend towards large pages including multimedia content. In addition, today's web pages are created dynamically, i.e., that the content is downloaded from web servers spread all around the world. Finally, we discuss new web traffic models and present the parameters gathered from our measurements.