Abstract
Wireless LANs carry a mixture of traffic, with different delay and throughput requirements. The usual way to provide low-delay services is to give priority to such traffic. However this creates an incentive for throughput sensitive traffic also to use this service, which degrades overall network performance. We propose to allow applications to trade off delay for throughput, without giving preference to one class over another, by simultaneously scaling IEEE 802.11's CWmin and TXOP limit parameters. We provide a model of this scheme with two traffic classes, and show that increasing CWmin and TXOP limit in equal proportion reduces, but does not eliminate, the incentive for bulk data users to use the low-delay service. We show that subtracting a small constant from CWmin eliminates this incentive, while still giving improved performance to both classes.