Performance bounds for flow control protocols

In this paper, we discuss a simple conceptual framework for analyzing the f low of data in integrated services networks. The framework allows us to eas ily model and analyze the behavior of open loop, rate based flow control pr otocols, as well as closed loop, window based how control protocols. Centra l to the framework is the concept of a service curve element, whose departu re process is bounded between the convolution of the arrival process with a minimum service curve and the convolution of the arrival process with a ma ximum service curve. Service curve elements can model links, propagation de lays, schedulers, regulators, and window based throttles. The mathematical properties of convolution allow us to easily analyze complex configurations of service curve elements to obtain bounds on end-to end performance. We d emonstrate this by examples, and investigate tradeoffs between buffering re quirements, throughput, and delay, for different flow control strategies.