A new fixed-rate layered multicast congestion control algorithm called FLMCC is proposed. The sender of a multicast
session transmits data packets at a fixed rate on each layer, while receivers each obtain different throughput by
cumulatively subscribing to deferent number of layers based on their expected rates. In order to provide TCP-friendliness
and estimate the expected rate accurately, a window-based mechanism implemented at receivers is presented. To achieve
this, each receiver maintains a congestion window, adjusts it based on the GAIMD algorithm, and from the congestion
window an expected rate is calculated. To measure RTT, a new method is presented which combines an accurate
measurement with a rough estimation. A feedback suppression based on a random timer mechanism is given to avoid
feedback implosion in the accurate measurement. The protocol is simple in its implementation. Simulations indicate that
FLMCC shows good TCP-friendliness, responsiveness as well as intra-protocol fairness, and provides high link
The current routing and wavelength assignment (RWA) algorithms in optical switching (OBS) networks usually adopt the shortest path between the source-destination pairs as the routes and assign wavelengths hop-by-hop. There are two main problems exist in theses algorithms: (1) If there are common links among the shortest paths of different source-destination pairs, the one-way reservation protocol may cause congestion on these links while other links are underutilized, which may deteriorate the network performance, especially in an unsymmetrical network. (2) Few RWA algorithms take the fault recovery into consideration, which is
important for the network to operate smoothly. An ant system based RWA algorithm is proposed in this paper to resolve these two problems. The destination nodes send ACKs back for each successfully received burst control packet (BCP). The ACKs are
feed back along the same path as the one through which BCPs are forwarded. ACKs leave some "pheromone" along the path. The coming bursts will choose the output links with the probability proportioned to their pheromone intensity. Numerical results obtained from simulation show that our RWA algorithm can find the optimal routes adaptively and get a better burst drop probability performance compared with current RWA algorithms in an unsymmetrical network. Furthermore, our RWA algorithm is robust for fault recovery. When there are failures on some fibers, the bursts can be dynamically deflected to a suitable route without any extra information exchange among the switching nodes.
A single rate multicast congestion control for streaming media applications called Binomial congestion control At Receivers for Multicast (BARM) is proposed. Combining aspects of window-based and rate-based congestion control, the protocol shifts most of the congestion control mechanisms to multicast receivers. The main features of BARM are as follows. (1) The protocol adopts binomial algorithm (k=l=0.5, α=0.28, β=0.2 for our implementation) to adjust congestion window, which not only provides TCP-friendliness but decreases abrupt rate fluctuations, making it suitable for real time streaming media multicast applications. (2) The binomial algorithm is executed at the receivers instead of at the sender; to do this, a congestion window is maintained and updated separately by each receiver. Hence the protocol not only has a better scalability but reduces the burden of the sender significantly and is suitable to Client/Server model. (3) The congestion window is converted to the expected receiving rate which is then fed back to the sender if permitted. Compared to window feedback scheme, rate feedback scheme is simpler and increases the scalability. (4) The representative approach is used to suppress the feedback implosion. Simulations results indicate that BARM shows good fairness, TCP-friendliness, smoothness, scalability, and acceptable responsiveness.