A research topic that I am presently working on with a grad student at Kent State University. The idea behind pre-fetching is that for each web page visited on the Internet, the page is checked for hyperlinks to other web pages or other media types (such as mp3, wav, etc.). Each web page is assigned a priority which is based on the ratio between the size of the media and the number of accesses to that specific media object. The media with the highest priority is the one that is pre-fetched. A more advanced version of this algorithm is to calculate the size of a lead segment to be pre-fetched. The size of the lead segments is based on the amount of bandwitdh being utilized for pre-fetching, and the priority of the media to be pre-fetched. Using lead segments reduces the amount of bandwidth used in pre-fetching, and allows for fewer wasted bits.

Log in or register to write something here or to contact authors.