Stabilization of max–min fair networks without per-flow state
Let a flow be a sequence of packets that are sent from a source computer to a destination
computer. In this paper, we consider the fair allocation of bandwidth to each flow in a
computer network. We focus on max–min fairness, which assigns to each flow the largest
possible bandwidth that avoids affecting other flows. What distinguishes our approach is that
routers only maintain a constant amount of state, ie, no per-flow state is maintained. This is
consistent with trends in the Internet (such as the proposed Differentiated Services Internet …
computer. In this paper, we consider the fair allocation of bandwidth to each flow in a
computer network. We focus on max–min fairness, which assigns to each flow the largest
possible bandwidth that avoids affecting other flows. What distinguishes our approach is that
routers only maintain a constant amount of state, ie, no per-flow state is maintained. This is
consistent with trends in the Internet (such as the proposed Differentiated Services Internet …
Let a flow be a sequence of packets that are sent from a source computer to a destination computer. In this paper, we consider the fair allocation of bandwidth to each flow in a computer network. We focus on max–min fairness, which assigns to each flow the largest possible bandwidth that avoids affecting other flows. What distinguishes our approach is that routers only maintain a constant amount of state, i.e., no per-flow state is maintained. This is consistent with trends in the Internet (such as the proposed Differentiated Services Internet architecture). In addition, to provide a high degree of fault-tolerance, we ensure our approach is self-stabilizing, that is, it returns to a normal operating state after a finite sequence of faults.
Elsevier
Showing the best result for this search. See all results