Workload Analysis of a Video-on-Demand Service with a Wide Range of Subjects and Lengths

X.G. Pañeda, D. Melendi, R. García, V.G. García, and J. Pérez (Spain)


Video-on-demand, streaming, analysis, workload, model.


This paper presents the analysis performed on the video-on-demand service (LNE TV), which is part of the digital version of one of the most important newspapers in Spain. Its main special characteristic is the wide range of subjects (news, music, culture, tourism, nature, sports, etc) and lengths of the offered contents (from 2 minutes to 2 hours), which make it one interesting case study. Different elements have analyzed such as, popularity analysis, session analysis, delivered time, etc. The study point out interesting results about the length dependence, interactions appearing, popularity of the videos, etc, which are compared with the results obtained in the previous, generally developed on educational environments (services or users). The more accurate distribution is estimated and, with the obtained results, a behaviour user model has been performed. This model is oriented to services with different types of information and lengths for the videos. This study has been performed thanks to an access log database with more than 80.000 reproductions on almost 700 videos stored along three years. The conclusions of the study are basic to improve the service configuration and content selection. Moreover, they can be used to develop service models to video-on-demand services, which can help administrators to predict future situations and avoid performance problems.

Important Links:

Go Back