Title :
Moving average based predictors for MPEG-4 VBR traffic sources
Author :
Narasimhan, Harikrishna ; Tripuraribhatla, Raghuveera ; Easwarakumar, K.S.
Author_Institution :
Dept. of Comput. Sci. & Eng., Anna Univ. Chennai, Chennai, India
Abstract :
Dynamic allocation of bandwidth allows us to maintain an agreed quality of service while streaming multimedia content in a network. This can be achieved by predicting future traffic in advance and allocating resources accordingly. In this paper, we propose new prediction techniques for MPEG-4 encoded variable bit rate video traffic based on the concept of moving average and extend them further using the gradient-descent approach. The resultant predictors are both simple and accurate and suitable for realtime prediction. We use the NLMS technique as a base-line predictor for our comparative study and show a performance improvement of about 11%.
Keywords :
gradient methods; least mean squares methods; media streaming; moving average processes; quality of service; telecommunication traffic; variable rate codes; video coding; MPEG-4 VBR traffic sources; NLMS technique; bandwidth dynamic allocation; gradient-descent approach; moving average based predictor; multimedia streaming; prediction technique; quality of service; variable bit rate video traffic; MPEG-4; NLMS filter; gradient-descent; linear predictor; moving average; realtime prediction;
Conference_Titel :
GLOBECOM Workshops (GC Wkshps), 2010 IEEE
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4244-8863-6
DOI :
10.1109/GLOCOMW.2010.5700460