Less-than-best-effort services: pricing and scheduling

Abstract

In recent years, the notion of a service offering a degraded performance with respect to the best-effort service traditionally found in IP networks has gained acceptance among network researchers. Such a less-than-best-effort (LBE) service may he considered as another way of providing a differentiated quality of service, following A. Odlyzko's damaged goods for the Internet approach. In this paper we are interested in evaluating, from a pricing perspective, the implications of the two scheduling models commonly proposed for building a LBE service-namely, priority queueing and generalized processor sharing (GPS). In particular, we focus on the network operator's issue of maximizing her revenue. We wish to study, for each scheduler, how to set prices and, especially, the impact that a given queueing model may have on revenues when users are mostly sensitive to delay. Drawing on previous work by Mandjes (2003), we present analytical expressions of the revenue earned by the network operator, when a GPS scheduler is used. A comparison of optimal revenues shows that: (a) Priority Queueing is more efficient, in economic terms, than both a GPS scheduler and a simple FIFO queue, that is, a network with no service differentiation; (b) revenues are lower with a GPS scheduler than with a FIFO queue. These results may have implications both on the practical implementation of LBE services and on the Paris Metro Pricing proposal by Odlyzko (1999).