Effective bandwidth vectors for multiclass traffic multiplexed in partitioned buffer

Kulkarni, Vidyadhar G.; Gün, Levent; Chimento, P.F.

doi:10.1109/49.400659

Cited by 28 publications

(26 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spectral solution to (2) is given by (3) where ( , ) is an eigenvalue/eigenvector pair. Such pairs are solutions to the eigenvalue problem (4) After solving all the coefficients in (3) from boundary conditions [4], [9], the loss rate of class fluid can be calculated by (5) where the symbol denotes the inner product of the vectors and is the vector in which all elements are unity.…”

Section: Fluid Model Analysismentioning

confidence: 99%

“…For , let . 2 According to [4] and [9], the governing differential equations of the buffer sharing system is (2) where , and is the identity matrix. The spectral solution to (2) is given by (3) where ( , ) is an eigenvalue/eigenvector pair.…”

Section: Fluid Model Analysismentioning

confidence: 99%

“…For the case of intrabuffer priority, Elwalid and Mitra [9] developed fluid models for the analysis of an asynchronous transfer mode (ATM) loss-priority system, where each ATM connection has some cells designated the high priority and others designated the low priority, and all cells are buffered in a single first-in-first-out (FIFO) queue, with the low priority cells being discarded when the queue length exceeds a predefined threshold. A generalization of this model with two or more loss priorities per connection was analyzed by Kulkarni et al [4]. They showed that the effective bandwidth concept can be extended to effective bandwidth vectors and used for admission control.…”

Section: Introductionmentioning

confidence: 99%

“…Based on the theoretical study in [4], this paper elaborates on the work in [11]. The minimal channel capacity obtained from the buffer partitioning optimization is defined as the effective bandwidth of the multiclass Markov-modulated fluid source.…”

Section: Introductionmentioning

confidence: 99%

“…Typically in a DiffServ core router, three buffers are used to achieve the premium service [2], the assured service [3], and the best-effort service, which are served with high, medium, and low priority, respectively. The other level of priority, intrabuffer priority, is to serve traffic with a partitioned buffer [4], which provides different loss priorities while keeping the order of packets from the same microflow. The buffer for the assured service is usually a partitioned buffer.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Effective bandwidth of multiclass Markovian traffic sources and admission control with dynamic buffer partitioning

Cheng

Zhuang

Global Telecommunications Conference, 2002. GLOBECOM '02. IEEE

View full text Add to dashboard Cite

Abstract-We investigate the statistical multiplexing and admission control for a partitioned buffer, where the traffic is generated by multiclass Markov-modulated fluid sources. Each of the sources has ( 1) classes at each state. The quality of service (QoS) is described by the packet loss probability for each class. The buffer is partitioned with 1 thresholds to provide the loss priorities. Extending the effective bandwidth concept to such a buffer system is a challenging topic. In this paper, we find the minimal effective bandwidth in the asymptotic regime of large buffers and small loss probabilities by optimally setting the partition thresholds. The minimal effective bandwidth achieves efficient resource utilization and can be used to do admission control for heterogeneous multiclass Markovian sources in an additive way. The buffer partition thresholds are dynamically adjusted according to the input traffic load to guarantee QoS. Numerical analysis and simulation results verify the QoS satisfaction and the obvious improvement of resource utilization compared with previously published results, when the minimal effective bandwidth is used for resource allocation with the proposed dynamic buffer partitioning techniques.Index Terms-Differentiated services (DiffServ), dynamic buffer partitioning, effective bandwidth, loss priorities, multiclass Markovian traffic sources.

show abstract

Section: Fluid Model Analysismentioning

confidence: 99%

Section: Fluid Model Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Effective bandwidth of multiclass Markovian traffic sources and admission control with dynamic buffer partitioning

Cheng

Zhuang

Global Telecommunications Conference, 2002. GLOBECOM '02. IEEE

View full text Add to dashboard Cite

show abstract

Statistical Multiplexing

Chandra

2003

Wiley Encyclopedia of Telecommunications

View full text Add to dashboard Cite

Statistical multiplexers play a central role in the design of high‐speed multiservice telecommunications networks. As network links reach capacities of terabits per second, the multiplexing of a large number variable rate voice, video and data sources on a common channel can achieve significant savings in the bandwidth consumed by each source. This resource sharing paradigm must be examined by considering the traffic characteristics, performance requirements and multiplexing system parameters. Traffic on broadband networks is characterized by complex features that include correlation over many time scales, significant dispersion about the mean rate, nonstationary variations in average rate and variance and in some cases deterministic fluctuations. These features render classical Poisson traffic based approaches to performance analysis inaccurate. This paper presents a overview of new traffic models and performance analysis techniques for statistical multiplexing systems. The application of renewal processes, Markov chains, time‐series models and self‐similar processes as traffic models are discussed. Analytic, computational and approximate performance analyses of statistical multiplexers are reviewed. The design of admission control algorithms for controlling statistical multiplexing performance using moment matching methods, fluid flow approximations, large‐deviation principles and effective bandwidth approximations are discussed.

show abstract

Statistical Time Division Multiplexing

Chandra

2007

Handbook of Computer Networks

View full text Add to dashboard Cite

Effective bandwidth vectors for multiclass traffic multiplexed in partitioned buffer

Abstract: Abstract-

Cited by 28 publications

References 13 publications

Effective bandwidth of multiclass Markovian traffic sources and admission control with dynamic buffer partitioning

Effective bandwidth of multiclass Markovian traffic sources and admission control with dynamic buffer partitioning

Statistical Multiplexing

Statistical Time Division Multiplexing

Contact Info

Product

Resources

About