This paper investigates how a p2p television platform can take advantageof the presence of frequent channel viewers to grant thema more satisfying service than to less regular spectators. The ideawe explore is to learn beforehand about the users’ interests, in orderto cluster them in groups that display different behaviors; then,the video chunk scheduling algorithm of the p2p overlay is altered,with the aim of serving frequent spectators in a privileged manner,providing them with a faster access to the selected channel. An analyticalmodel is developed, to capture the difference in startup delaythat the proposed changes introduce; several additional performancemetrics are numerically determined, in order to thoroughly size upthe performance of different groups of viewers. The obtained resultsshow that a clear service differentiation is achieved and also quantifythe effects that the setting of different system parameters have on theamount of such gap.
|Numero di pagine||0|
|Stato di pubblicazione||Published - 2014|
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
- Human-Computer Interaction