We introduce LT codes, the first rateless erasure codes that are very efficient as the data length grows.

In this paper we introduce TFMCC, an equation-based multicast congestion control mechanism that extends the TCP-friendly TFRC protocol from the unicast to the multicast domain. The key challenges in the design of TFMCC lie in scalable round-trip time measurements, appropriate feedback suppression, and in ensuring that feedback delays in the control loop do not adversely affect fairness towards competing flows. A major contribution is the feedback mechanism, the key component of end-to-end multicast congestion control schemes. We improve upon the well-known approach of using exponentially weighted random timers by biasing feedback in favor of low-rate receivers while still preventing a response implosion. We evaluate the design using simulation, and demonstrate that TFMCC is both TCP-friendly and scales well to multicast groups with thousands of receivers. We also investigate TFMCC's weaknesses and scaling limits to provide guidance as to application domains for which it is well suited. Keywords congestion control, multicast, single-rate, TCP-friendliness, feedback suppression 1.

New trends in communication, in particular the deployment of multicast and real-time audio/video streaming applications, are likely to increase the percentage of non-TCP traffic in the Internet. These applications rarely perform congestion control in a TCP-friendly manner, i.e., they do not share the available bandwidth fairly with applications built on TCP, such as web browsers, FTP- or email-clients. The Internet community strongly fears that the current evolution could lead to a congestion collapse and starvation of TCP traffic. For this reason, TCP-friendly protocols are being developed that behave fairly with respect to co-existent TCP flows. In this article, we present a survey of current approaches to TCP-friendliness and discuss their characteristics. Both unicast and multicast congestion control protocols are examined, and an evaluation of the different approaches is presented.

Abstract—The proliferation of applications that must reliably distribute large, rich content to a vast number of autonomous receivers motivates the design of new multicast and broadcast protocols. We describe an ideal, fully scalable protocol for these applications that we call a digital fountain. A digital fountain allows any number of heterogeneous receivers to acquire content with optimal efficiency at times of their choosing. Moreover, no feedback channels are needed to ensure reliable delivery, even in the face of high loss rates. We develop a protocol that closely approximates a digital fountain using two new classes of erasure codes that for large block sizes are orders of magnitude faster than standard erasure codes. We provide performance measurements that demonstrate the feasibility of our approach and discuss the design, implementation, and performance of an experimental system. Index Terms—Content delivery, erasure codes, forward error correction, reliable multicast, scalability. I.

Traditional approaches to receiver-driven layered multicast have advocated the benefits of cumulative layering, which can enable coarse-grained congestion control that complies with TCP-friendliness equations over large time scales. In this paper, we quantify the costs and benefits of using non-cumulative layering and present a new, scalable multicast congestion control scheme which provides a fine-grained approximation to the behavior of TCP additive increase / multiplicative decrease (AIMD). In contrast to the conventional wisdom, we demonstrate that finegrained rate adjustment can be achieved with only modest increases in the number of layers and aggregate bandwidth consumption, while using only a small constant number of control messages to perform either additive increase or multiplicative decrease.

We survey constructions and applications of digital fountains, an abstraction of erasure coding for network communication. Digital fountains effectively change the standard paradigm where a user receives an ordered stream of packets to one where a user must simply receive enough packets in order to obtain the desired data. Obviating the need for ordered data simplifies data delivery, especially when the data is large or is to be distributed to a large number of users. We also examine barriers to the adoption of digital fountains and discuss whether they can be overcome.

A significant impediment to deployment of multicast services is the daunting technical complexity of developing, testing and validating congestion control protocols fit for wide-area deployment. Protocols such as pgmcc and TFMCC have recently made considerable progress on the single rate case, i.e. where one dynamic reception rate is maintained for all receivers in the session. However, these protocols have limited applicability, since scaling to session sizes beyond tens of participants necessitates the use of multiple rate protocols. Unfortunately, while existing multiple rate protocols exhibit better scalability, they are both less mature than single rate protocols and suffer from high complexity.

Abstract — In this paper, we design SIM, a protocol that integrates three distinct mechanisms – Selective participation, Intra-group transmission adjustment, and Menu adaptation – to solve the general multicast congestion control problem. We argue that only a solution that includes elements of each mechanism can scale and adapt to heterogeneity in network and receiver characteristics. In our protocol, these mechanisms operate at different time scales and distribute the responsibility of adaptation to different entities in the network. Per our knowledge, SIM is the first protocol for layered multicast that adjusts not only the subscription levels of the receivers but also the transmission rates of the layers. We show that SIM is efficient and stable in the presence of heterogeneous receivers and dynamic changes in the bottlenecks and session membership. SIM also outperforms RLM in terms of stability and efficiency. 1

Layered multicast is a common approach for dissemination of audio and video in heterogeneous network environments. Layered multicast schemes can be classified into two categories -- feedback-based and feedback-free -- depending on whether or not the scheme delivers feedback to the sender of the multicast session. Advocates of feedback-based schemes claim that feedback is necessary to match the heterogeneous receiver capabilities e#ciently. Supporters of feedback-free schemes believe that feedback introduces significant complexity and that a moderate amount of additional layers can balance any benefit the feedback provides. Surprisingly, there has been no systematic evaluation of these claims. This paper provides a quantitative comparison of feedbackbased and feedback-free layered multicast schemes with respect to aligning the provided service to the capabilities of heterogeneous receivers. We discover realistic scenarios when feedback-free schemes require a very large number of additional layers to match the performance of feedbackbased schemes. Our studies also demonstrate that a lightweight feedback-based scheme can o#er substantial improvement in performance over feedback-free schemes and can closely approximate the e#ciency achieved by the optimal feedback-based scheme.

Existing approaches for multirate multicast congestion control are either friendly to TCP only over large time scales or introduce unfortunate side eects, such as signi cant control trac, wasted bandwidth, or the need for modi cations to existing routers. We advocate a layered multicast approach in which steady-state receiver reception rates emulate the classical TCP sawtooth derived from additive-increase, multiplicative decrease (AIMD) principles. Our approach introduces the concept of dynamic stair layers to simulate various rates of additive increase for receivers with heterogeneous round-trip times (RTTs), facilitated by a minimal amount of IGMP control trac. We employ a mix of cumulative and non-cumulative layering to minimize the amount of excess bandwidth consumed by receivers operating asynchronously behind a shared bottleneck. We integrate these techniques together into a congestion control scheme called STAIR which is amenable to those multicast applications which can make eective use of arbitrary and time-varying subscription levels. 1