Dynamic utility-based bandwidth allocation policies: the case of overloaded network

Abstract

Efficient and reliable bandwidth allocation remains an important open issue in the management of networks that aim to offer a guaranteed quality of service (QoS). Guaranteeing QoS to incoming requests means that users explicitly specify certain requirements such as throughput, loss or delay. It also means that the provider needs to be prepared to compensate for transient outages or overloads and re-allocate resources according to priorities. Dynamic bandwidth allocation can be used to assure that high priority requests can be always routed through relatively favorable paths within a differentiated services environment. In this paper we introduce a utility-based QoS model and a generalized bandwidth allocation scheme which accounts for the users of QoS requirements. We analyze the dynamic and static bandwidth allocation policies in the presence of four types of traffic each described with its utility value when the network experiences overloads. Our approach allows a service provider to differentiate between different types of customers based on their priority or the service charges that they pay, in order to offer real time services, to provide QoS guarantees for multimedia traffic and to guarantee stability even in overloaded conditions.