This paper is the sequel of two previous papers describing and analyzing partially blocking-queueing systems. In those papers Blaabjerg et al. (see Proc. of the IEEE International Conference on Communication Systems, ICCS '96, Singapore, 1996 and Proc. of the 5th IFIP International Conference on Telecommunications Systems Performance Modelling, Nashville, TN, USA, 1997) proposed the extension of the classical multirate circuit switched loss model in order to model and analyze on the call level ATM systems supporting best effort type service classes, such as the ABR or UBR service classes. After a brief review of the basic modelling concepts, in this paper we are concerned with optimal call admission control, (CAC) of CBR/VBR and ABR/UBR calls in the sense that we want to maximize the revenue on a single ATM link when both QoS guaranteed and best effort service classes are present. We formulate the problem as a Markov decision problem and find that the concept of intelligent blocking is useful in this context. We solve this optimization task by policy iteration to find the blocking states of the link. This modelling framework (in its present form and by extensions) allows one to study the impact of pricing policies on CAC and fairness.

A mathematical model is presented that provides a well-defined formulation of the logical configuration problem of ATM networks (the carriers of future B-ISDN) with the objective of maximizing the total expected network revenue, given the physical network parameters and the traffic requirements of each virtual subnetwork. A two-phase solution procedure is developed in which the decision variables are the logical link capacities that specify the logical decomposition into virtual subnetworks, and the load sharing parameters. The first phase of the solution finds a global optimum in a rougher model. The second phase uses this as an initial point for a gradient-based hill climbing that applies the partial derivatives of the network revenue function obtained in a more refined model.>

Recent research has shown that fluid-flow queueing models accurately determine the burst level component of the ATM multiplexer process, and fluid models therefore constitute an efficient tool for the investigation of admission control in ATM networks. This article first gives a review of Markov-driven fluid queues with special attention given to the heterogeneous on/off model. Then an approximation procedure in which the original heterogeneous arrival process is replaced by a homogeneous birth-death arrival process is presented. The substitution is based on matching statistical parameters. Finally, the approach is evaluated by numerical examples.>

The authors consider statistical multiplexing of on/off sources in an asynchronous transfer mode (ATM) network and its implications on traffic control. The periodic on/off source is used as a worst case output from the traffic enforcement algorithm, and the queue receiving information from a number of independent periodic on/off sources is studied with simulation results and analytical methods. The decomposition of the queuing process into a cell scale and a burst scale component is illustrated. A comparison with the exponentially distributed on/off queue is carried out, and a simple and versatile approximation is provided on which an admission control scheme based on peak, mean and burst duration can be based. Some implications on buffer dimensioning and traffic control are discussed.>