The asymptotic behaviour of a connection transmitting packets into a network according to a general additive-increase multiplicative-decrease (AIMD) algorithm is investigated. The stationary properties of this algorithm are analyzed when the rate of occurrence of clumps (loss of packets) becomes arbitrary small. From a probabilistic point of view, it is shown that exponential functionals associated to compound Poisson processes play a key role. A formula for the fractional moments and some density functions are obtained. Analytically, to derive the explicit expression of the distributions involved, the natural framework of this study turns out to be the q-calculus. Different loss models are then compared using concave ordering. It is shown, quite surprisingly, that for a fixed loss rate, the correlated loss model has higher throughput than an uncorrelated loss one.