Impact of Traffic Aggregation on Network Capacity and Quality of Service

The impact of traÆc handling mechanisms on network capacity and supporting of Quality of Service (QoS) in the Internet is studied. The emergence of applications with diverse throughput, loss and delay requirements requires a network that is capable of supporting di erent levels of service as opposed to the single best-e ort service that was the foundation of the Internet. As a result the Integrated Services (perow) and Di erentiated Services (Di serv) models have been proposed. The perow model requires resource reservation on a perow basis while the Di serv model requires no explicit reservation of bandwidth for individual ows and instead relies on a set of pre-de ned service types to provide QoS to applications. Flows are grouped into aggregates having the same QoS requirements and the aggregates are handled by the network as a single entity with no ow di erentiation. We refer to this type of handling as semi-aggregate or class-based. The Best-E ort model does not perform any di erentiation and handles all traÆc as a single aggregate. Each of these traÆc handling models can be used to meet service guarantees of di erent traÆc types, the major di erence being in the quantity of network resources that must be provided in each case. The cross-over point at which the three approaches of aggregate traÆc management, semi-aggregate traÆc management and perow traÆc management become equivalent is found. Speci cally, we determine the network capacity required to achieve equivalent levels of performance under these three traÆc management approaches. We use maximum end-to-end delay as the QoS metric and obtain analytic expressions for network capacity based on deterministic network analysis. One key result of this work is that on the basis of capacity requirements, there is no signi cant di erence between semi-aggregate traÆc handling and perow traÆc handling. However Best-E ort handling requires more capacity that may be several orders of magnitude greater than perow handling.