Media synchronization in multimedia Web using a neuro-fuzzy framework

In this paper, we consider the problem of multimedia synchronization in a W eb environment. The workload generated by the multimedia server during a We b session exhibits variations that are quite different from the traffic flu ctuation offered by a single media stream, e.g., a variable bit rate (VBR) video. We propose a set of parameters that can be used to characterize the workload generated by the multimedia server in a Web-type browsing environm ent. The workload characterization scheme is subsequently used in designing a server-based synchronization scheme, The problem of scheduling multimedi a information to ensure media synchronization in a Web environment is ident ified as a multicriteria scheduling problem, which is NP-hard, The ability of fuzzy control to deal with multivariables makes it a good al ternative for the multicriteria scheduling problem considered in this paper . Consequently, we propose a neuro-fuzzy scheduler (NFS) that makes an inte lligent compromise among multieriteria by properly combining some schedulin g heuristics. Performance of the NFS is compared with several known heurist ics and a branch and bound algorithm. The results show that the proposed NF S can dynamically adjust to the varying workload quite well.