Delay calculus for differentiated services networks

Abstract

The differentiated service architecture is proposed as a scalable approach to QoS for IP networks. Therefore it is based on the aggregate (per class) scheduling of packets, but it aims at providing QoS to single flows. In particular the expedited forwarding (EF) per hop behavior (PHB) and the related premium service have been defined in order to provide determinist QoS guarantees to IP flows: zero loss and very low delay and jitter. Hence a possible approach to characterize and to dimension a network using the EF PHB is the worst case analysis. In this work we propose a worst case calculus that, permits to model any kind of network that doesn't perform per flow scheduling, taking into account both the network topology and the characterization of input flows. Particularly, the calculus provides the output arrival curve and the maximum delay at each network node. Our calculus improves the accuracy on the delay and arrival curve evaluation with respect to the previous approaches. The guidelines for the application of the calculus are given and some numerical results are carried out and compared to those obtained by previous models.