Traffic rate and shape control with queue threshold congestion recognition

This paper presents analysis of a congestion control scheme in which a multiplexer notifies upstream traffic flows when its buffer level crosses a preset threshold. Upon notification, the traffic streams feeding the buffer are reshaped to a form less likely to cause buffer overflow which can involve rate or burstiness restrictions, or a combination of the two. The traffic is modeled by two Markov modulated rate processes (MMRPs), one for above and one for below the threshold, and we use an iterative fluid approximation to determine the buffer occupancy distribution. Simulation results verify the approach, and the analysis is used to study the effect of varying the threshold and shaping function.