Per Packet Value: A Practical Concept for Network Resource Sharing

Abstract

Governing how network resources are shared among various traffic flows is not a completely solved problem. The ideal system can implement a wide variety of detailed and flexible policies; enforces those policies under all possible offered traffic combinations and scales well with the number of flows. In this paper we introduce a framework that approximates the ideal system well. It consists of flow-aware Packet Value marking at the edges and flow-unaware operation inside the network. We show that inside the network relatively simple scheduling and AQM algorithms operating solely on Packet Value are suitable to implement the policies set at the network edge. We also discuss, how the framework can be used to support resource sharing over radio networks (where the cost of transmission varies) and how it enables load balancing, resource balancing and optimal network-wide load distribution.