With e!ective bandwidth concept encapsulating cell-level behaviour, asynchronous transfer mode (ATM) network design and analysis at the call-level may be formulated in the framework of circuit-switched loss networks. In this paper, we develop an analytical framework for a kind of multiparty videocon
A priority leaky-bucket regulator for virtual path traffic in ATM networks
✍ Scribed by J. Zeng; N.H. Loukas; L. Merakos
- Publisher
- Elsevier Science
- Year
- 2001
- Tongue
- English
- Weight
- 403 KB
- Volume
- 24
- Category
- Article
- ISSN
- 0140-3664
No coin nor oath required. For personal study only.
✦ Synopsis
In integrated services networks (B-ISDN/ATM) incoming traf®c streams with different Quality of Service (QoS) requirements, sharing a single contract for use of a policed virtual path, may be jointly regulated on the basis of their type and QoS requirements to make the best use of available bandwidth in the path. The shaping/policing mechanism may use the information about the network policer located at the User-Network Interface (UNI) to perform policing with a form of priority service to ensure satisfactory levels of cell loss and delay for both realtime and non-real time traf®c. This paper proposes and analyzes such a priority, buffered leaky-bucket mechanism for shaping/policing highpriority and low-priority sources, which share an ATM virtual path under a single, common user-network connection contract. The proposed priority traf®c regulator maintains a dedicated cell buffer for each type of traf®c to be able to trade off cell delay and loss (or tagging) on the basis of the QoS requirements for each priority class. The analysis adopts a Discrete Batch Markovian Arrival Process (D-BMAP) model for both high-priority and low-priority sources. It is shown that the system model has an M/G/1 type queuing structure, which is exploited for the computation of the joint buffer content distribution and cell loss probabilities of the high-priority and low-priority traf®c streams. The obtained numerical results capture the effect of the shaper/policer and source parameters on the cell loss performance, and may be used for design optimization. A comparison of the priority leaky-bucket with the classical single buffer leaky-bucket regulator is carried out to quantify the improvement in terms of bandwidth utilization.
📜 SIMILAR VOLUMES