1Pricing Network Resources for Adaptive Applications in a Differentiated Services Network

Abstract — The Differentiated Services framework (DiffServ) has been proposed to provide multiple Quality of Service (QoS) classes over IP net-works. A network supporting multiple classes of service also requires a differentiated pricing structure. In this work, we propose a pricing algo-rithm in a DiffServ environment based on the cost of providing different levels of quality of service to different classes, and on long-term average user resource demand of a service class. We also integrate the proposed service-dependent pricing scheme with a dynamic pricing and service ne-gotiation environment by considering a dynamic and congestion-sensitive pricing component. Pricing network services dynamically based on the level of service, usage, and congestion allows a more competitive price to be of-fered, allows the network to be used more efficiently, and provides a natural and equitable incentive for applications to adapt their service requests ac-cording to network conditions. We develop a simulation framework to com-pare the performance of a network supporting congestion-sensitive pricing and adaptive service negotiation to that of a network with a static pricing policy. Adaptive users adapt to price changes by adjusting their sending rate or selecting a different service class. We also develop the demand be-havior of adaptive users based on a physically reasonable user utility func-tion. Simulation results show that a congestion-sensitive pricing policy cou-pled with user rate adaptation is able to control congestion and allows a ser-vice class to meet its performance assurances under large or bursty offered loads, even without explicit admission control. Users are able to maintain a stable expenditure, and allowing users to migrate between service classes in response to price increases further stabilizes the individual service prices. When admission control is enforced, congestion-sensitive pricing still pro-vides an advantage in terms of a much lower connection blocking rate at high loads. I