Dear Lucia, As Ihsan mentioned in another thread of discussion, we do have developed a synthetic generator of individual traces. We consider 6 kinds of realistics behaviors (in terms of content preference, watching hours, daily watching time, ...) extracted from a sociological study.
Moreoever, we have shown that when generating a large population of users, our model fits well with models extracted from measurements performed over real systems. We have implemented our model in matlab and we just migrated it in Java so that it can be used to reproduce a realistic user behavior in concrete implementations of video streaming systems. We could provide it to you if needed. You can find further information in the paper mentioned by Ihsan and in the proceedings of IFIP/IEEE IM'11. Do not hesitate to contact us for any info/question. Best regards from France, Guillaume Hi all, I would like to inform you that we have developed a semi-markovian model of individual users in P2P live streaming systems. This model can be used for generating experimental workloads. We have a matlab and java implementation of the model. Please feel free to contact us if anybody is interested in its use. futher details can be found in this paper. ================================= Bonnet, G.; Ullah, I.; Doyen, G.; Fillatre, L.; Gaïti, D.; Nikiforov, I.; , "A Semi-Markovian Individual Model of Users for P2P Video Streaming Applications," New Technologies, Mobility and Security (NTMS), 2011 4th IFIP International Conference on , vol., no., pp.1-5, 7-10 Feb. 2011 doi: 10.1109/NTMS.2011.5721042 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5721042&isnumber=5720575 ================================== Best Regards, Ihsan ULLAH ------------------------------------------------------------------------------------------ PhD student Autonomic Networking Environment Team Charles Delaunay Institute Troyes University of Technology France _______________________________________________ p2p-hackers mailing list p2p-hackers@lists.zooko.com http://lists.zooko.com/mailman/listinfo/p2p-hackers
