A Decentralized Framework to Achieve . . .

We consider a flow control algorithm to allocate bandwidth in a network subject to throughput and fairness constraints. Our algorithm achieves a max-min fair allocation among contending users, and has desirable properties in that it can operate in a decentralized and asynchronous manner accounting in part for heterogeneity in round trip delays. The algorithm is simple in that, 1), the network links make local measurements of capacity and calculate local `explicit rates' which are fed back to sources without requiring knowledge of the number of on-going connections, while 2), sources adjust their transmission rate so as not to exceed the received explicit rate indication. The algorithm is designed to track a dynamic environment. We discuss its stability, convergence, and feasibility related to fair allocation and rate-based flow control. We also consider the role of sessions with priorities, and its use for `ABR flow control' in ATM networks