Title :
A new approach to video bandwidth prediction
Author :
McGarry, Michael P. ; Haddad, Rami ; McAlarney, John
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Akron, Akron, OH, USA
Abstract :
We discuss a fundamentally new approach to digital packetized video bandwidth prediction (i.e., bandwidth forecasting). This fundamentally new approach provides an accurate bandwidth forecast at the expense of increased queueing delay. We outline this new forecasting method we call feedforward bandwidth indication (FFBI), compare it to existing forecasting methods, and analyze the tradeoffs associated with its use. Finally, we outline future avenues of research.
Keywords :
bandwidth allocation; feedforward; multimedia communication; packet radio networks; queueing theory; telecommunication traffic; video coding; bandwidth forecasting; feedforward bandwidth indication; queueing delay; video bandwidth; Bandwidth; Channel allocation; Communication networks; Delay; Feedforward neural networks; Feeds; Neural networks; Telecommunication traffic; Video compression; Wavelet analysis; bandwidth forecasting; bandwidth prediction; multimedia networking; video traffic;
Conference_Titel :
Ultra Modern Telecommunications & Workshops, 2009. ICUMT '09. International Conference on
Conference_Location :
St. Petersburg
Print_ISBN :
978-1-4244-3942-3
Electronic_ISBN :
978-1-4244-3941-6
DOI :
10.1109/ICUMT.2009.5345560
