ThinStreams: an architecture for multicasting layered video

Abstract

*Multicast is a common method for distributing audio and video over the Internet. Since receivers are heterogeneous in processing capability, network bandwidth, and requirements for video quality, a single multicast stream is usually insufficient. A common strategy is to use layered video coding with multiple multicast groups. In this scheme, a receiver adjusts its video quality by selecting the number of multicast groups, and thereby video layers, it receives. Implementing this scheme requires the receivers to decide when to join a new group or leave a subscribed group. This paper presents a new solution to the join/leave problem using ThinStreams. In ThinStreams, a single video layer is multicast over several multicast groups, each with identical bandwidth. ThinStreams separates the coding scheme (i.e., the video layers) from control (i.e., the multicast groups), helping to bound network oscillations caused by receivers joining and leaving high bandwidth multicast groups.This work evaluates the join/leave algorithms used in ThinStreams using simulations and preliminary experiments on the MBONE. It also addresses fairness among independent video broadcasts and shows how to prevent interference between them.

The adaptive load service (ALS): an ABR-like service for the Internet

“…To avoid these problems, various proposals have been made for receiver based adaptation schemes using layered data distribution [32,20,34]. Those proposals are based on partitioning a data stream into a base layer, comprising the information needed to achieve the lowest quality representation and a number of enhancement layers.…”

CALM: congestion-aware layered multicast

“…Examples include broadcasts of live events, distance learning and training sessions, pre-recorded special TV reports, and made-for-the-web entertainment segments. Currently, one of the most popular solutions to the problem of large-scale multimedia broadcasts is layered multicast [2], [3], [4]. Layered multicast partitions the data into "layers" and transmits each layer on a distinct multicast channel (group).…”

“…Another problem related to IP multicast implementations is that each multicast group consumes state at routers. Protocols like Thinstreams [3] argue that many small layers allow for finer grained adjustments to congestion. However, this leads to large numbers of multicast groups per flow, with all their associated state information.…”

“…Using a join-timer similar to that of existing layered multicast protocols [2], [3], the receiver adds layers until the periodic collection messages indicate that the receiver's drop function is allowing too many packets through. In other words, join experiments must still be conducted; however, they are conducted independently and do not need to be announced to all other members.…”

“…With RLM-style methods (based on multiple multicast groups), all downstream group members must leave before any member benefits. The reduced router state resulting from a single tree combined with the ability of all receivers in a subtree to drop a layer simultaneously means that fine-grained layering similar to the encodings proposed in Thinstreams [3] is feasible.…”