Random Early Marking

| Random Early Marking (REM) consists of a link algorithm, that probabilistically marks packets inside the network, and a source algorithm, that adapts source rate to observed marking. The marking probability is exponential in a link congestion measure, so that the end{to{end marking probability is exponential in a path congestion measure. Marking allows a source to estimate its path congestion measure and adjusts its rate in a way that aligns individual optimality with social optimality. Because of the ner measure of congestion provided by REM, sources do not constantly probe the network for spare capacity, but settle around a globally optimal equilibrium, thus avoiding the perpetual cycle of sinking into and recovering from congestion. We rst derive REM as a distributed implementation of a gradient projection algorithm to maximize aggregate source utility over source rates. The gradient projection algorithm, whose stability and fairness have been proved even in an asynchronous environment, determines the macroscopic behavior of REM. We then illustrate through extensive simulations that REM is stable, fair and robust.