Online Traffic Smoothing for Delivery of VBR Media Streams

Traffic smoothing for delivery of online VBR media streams is one of the most important problems in designing multimedia systems. Given an available client buffer, a window size and a window-sliding size, previous window-based online smoothing methods try to reduce peak bandwidth allocated in each window. However, as bandwidths allocated in different windows are minimized independently, these methods require a large peak bandwidth for transmitting entire stream. In this paper, a new window-based method is proposed. It introduces two new ideas, the dynamic window-sliding size and the aggressive work-ahead, for delivery of online VBR media streams. Our ADWS (aggressive and dynamic window-sliding) method can automatically decide the suitable window-sliding sizes for different windows. Thus, the allocated peak bandwidth can be further reduced. By examining various media streams, ADWS is shown to be effective and efficient. Considering the online transmission of movie Star Wars with a 90 KB client buffer, ADWS yields 13% less in peak bandwidth, compared with the best-known window-based online smoothing algorithm SLWIN(1). Its computation cost (the window-sliding number) is 75% of that required by SLWIN(1). * This work was partially supported by NSC under grants NSC88-2213-E-001-011, NSC88-2213-E-001-012, and NSC88-2213-E-001-025. A primitive version of this work appeared in IEEE INFOCOM'99, NY, U.S.A.