A framework for bandwidth management in ATM networks-aggregate equivalent bandwidth estimation approach

Dziong, Zbigniew; Juda, Marek; Mason, L.

doi:10.1109/90.554728

Cited by 64 publications

(57 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…X k is the sample mean of y(n) at the k-th step and can be obtained from calculating (2). S 2 k is the sample variance of y(n) at the k-th step.…”

Section: Measurement Process Using Kalman Filtermentioning

confidence: 99%

“…In [8], the overview and the three-way taxonomy were provided. They commented that the admission control schemes proposed by [2] and [3] are simple and can achieve high bandwidth efficiency. These two schemes were both based on effective bandwidth and using measurement.…”

Section: Introductionmentioning

confidence: 99%

“…Many admission control schemes have been proposed to date (e.g, [2]- [7]). In [8], the overview and the three-way taxonomy were provided.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An On-Line Measurement-Based Admission Control for VBR Video Traffic in Wireless Multimedia Home Networks

Tseng

Chen

2007

NETWORKING 2007. Ad Hoc and Sensor Networks, Wireless Networks, Next Generation Internet

View full text Add to dashboard Cite

Abstract. Variable bit rate (VBR) video traffic with high data rate is expected to be the largest proportion of traffic carried by future wireless home networks. In order to guarantee quality-of-service (QoS) requirements of such type of VBR video traffic and improve channel utilization, this paper proposes an on-line measurement-based admission control scheme. The proposed scheme is designed based on the property of the aggregate VBR video traffic is lognormal distributed and consists of two main components which are measurement process and admission decision respectively. The measurement process applies a linear Kalman filter to estimate statistical parameters of aggregate VBR video traffic. Then, the estimated statistical parameters are used to calculate the effective bandwidth for admission decision. The proposed scheme is computational efficiently and accurate without much prior information of traffic. Simulation results confirm its accuracy and also show that the proposed scheme performs well for small number of connections as well as large number of connections.

show abstract

“…X k is the sample mean of y(n) at the k-th step and can be obtained from calculating (2). S 2 k is the sample variance of y(n) at the k-th step.…”

Section: Measurement Process Using Kalman Filtermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An On-Line Measurement-Based Admission Control for VBR Video Traffic in Wireless Multimedia Home Networks

Tseng

Chen

2007

NETWORKING 2007. Ad Hoc and Sensor Networks, Wireless Networks, Next Generation Internet

View full text Add to dashboard Cite

show abstract

“…On the other hand, for small buffer sizes Poisson distribution is the best approximation [70]. Finally, it is appropriate to say that all these approaches can be complemented with real measurements in order to dynamically determine the parameters of the different probabilistic distributions [72,73]. Thanks to this measurement-based adjustment, EBW becomes more adaptable and feasible.…”

Section: Equivalent Bandwidthmentioning

confidence: 99%

“…From these works, EBW became an important element of CAC with several applications reflected in the numerous articles found in the literature (see, e.g. [67][68][69][70][71][72][73][74]). This popularity is due to its capacity to simplify CAC for bursty-traffic services in wired ATM networks.…”

Section: Equivalent Bandwidthmentioning

confidence: 99%

Common Radio Resource Management Strategies for Quality of Service Support in Heterogeneous Wireless Networks

Calabuig¹

View full text Add to dashboard Cite

Nowadays several technologies coexist in the same area composing a heterogeneous system. Moreover, this fact is expected to become more and more accentuated with all new technologies that are currently being standardized. So far, generally users are who select the technology they are going to connect to, either configuring the user equipment or using different equipments. Nevertheless, this approach does not take the maximum advantage of the available resources. To this aim, a new set of strategies is necessary. These strategies must manage the radio resources of all technologies commonly and jointly, and they must ensure the satisfaction of users Quality of Service (QoS).Following this idea, this Thesis proposes two new algorithms. The first one is a Joint Dynamic Resource Allocation (JDRA) algorithm capable of allocating resources to users and distributing users among technologies at the same time. The algorithm is formulated as a multi-objective minimization problem that is solved using Hopfield Neural Networks (HNNs). HNNs are interesting because they are supposed to find suboptimal solutions in very short times. Nevertheless, actual implementations of HNNs in computers lose this fast response. For that reason, this Thesis analyses the causes and studies possible improvements.The second algorithm is a Joint Call Admission Control (JCAC) algorithm that admits and rejects users taking all technologies into account at the same time. The main difference with other proposed algorithms is that they decide on call admission in each technology separately. Thus, a previous mechanism is needed to select which technology users are going to connect to. On the other hand, the technique proposed in this Thesis is capable of deciding on call admission in the whole heterogeneous system. Therefore, users are not attached to any technology prior to admission.As a result, this Thesis paves the way to an efficient resource management in heterogeneous systems with new ideas and techniques. The functions of the Radio Resource Management (RRM) are divided into the JDRA and JCAC algorithms so they could work together. ResumenHoy en día existen varias tecnologías que coexisten en una misma zona formando un sistema heterogéneo. Además, este hecho se espera que se vuelva más acentuado con todas las nuevas tecnologías que se están estandarizando actualmente. Hasta ahora, generalmente son los usuarios los que eligen la tecnología a la que se van a conectar, ya sea configurando sus terminales o usando terminales distintos. Sin embargo, esta solución es incapaz de aprovechar al máximo todos los recursos. Para ello es necesario un nuevo conjunto de estrategias. Estas estrategias deben gestionar los recursos radio eléctricos conjuntamente y asegurar la satisfacción de la calidad de servicio de los usuarios.Siguiendo esta idea, esta Tesis propone dos nuevos algoritmos. El primero es un algoritmo de asignación dinámica de recursos conjunto (JDRA) capaz de asignar recursos a usuarios y de distribuir usuarios entre tecnologías al mismo ...

show abstract

Real-time VP bandwidth control for long-range-dependent traffic

Malomsoky

Vidács

Saitō

1999

Int. J. Commun. Syst.

View full text Add to dashboard Cite

The asymptotics of cell loss ratio (CLR) in the regime of large bu!ers are exponential and can be characterized by two parameters, the asymptotic constant and asymptotic decay rate. This result is very general, provided that the arrival process does not possess long-range dependence. As for the long-range dependent case (or equivalently, when the increment of the tra$c process is self-similar), the CLR decreases with the bu!er size sub-exponentially, and the two parameters are no longer adequate to capture this phenomenon. Recent results from the literature show that for self-similar tra$c models the tail of the stationary queue length distribution is Weibullian. Using these results, this paper proposes an algorithm for estimating the CLR in real time based on bu!er measurements, which works for both the long-range-and the short-range-dependent case. For this purpose, the notion of state-space representation of a single-server queue is introduced, and Bayesian regression analysis is applied to estimate the state variable of that system. Our approach does not require any models describing the statistics of the tra$c other than the asymptotic behaviour of the CLR. We describe how our method can be applied to VP bandwidth control by using results from simulation experiments.If the actual cell loss performance of an ATM output bu!er could be determined in real time, the rate of the server (that is, the VP bandwidth) could be adjusted such that the cell loss would be smaller than a pre-determined threshold. In Reference 6, Shioda and Saito presented a method for estimating the cell loss ratio in real time, and applied it to VP bandwidth estimation and call admission control. They utilized the large deviation result of Glynn and Whitt, that the CLR decays exponentially as the bu!er size increases. In this case the CLR (in the regime of large bu!ers) is characterized by two parameters, the so-called asymptotic constant and the asymptotic decay rate . As a result, an algorithm for estimating these coe$cients on an on-line basis from the bu!er measurement was proposed.The objective of this paper is to develop an algorithm (by reformulating the method proposed in Reference 6) for real-time VP bandwidth estimation, which works also in the case of longrange-dependent tra$c.The inherent correlations of a long-range-dependent stochastic process decay hiperbolically as the lag increases. As a result, the autocorrelation function is non-summable. This non-summability captures the intuition behind long-range dependence, namely, that while high-lag correlations are all individually small, the cumulative e!ect is of importance and gives rise to features which are drastically di!erent from those of the more conventional, i.e. short-range-dependent processes. The latter are characterized by an exponential decay of the correlations, resulting in a summable autocorrelation function.For long-range-dependent tra$c, the asymptotics for the queue length distributions are no longer exponential. Du$eld and O'Connell generalized the results o...

show abstract

A framework for bandwidth management in ATM networks-aggregate equivalent bandwidth estimation approach

Cited by 64 publications

References 24 publications

An On-Line Measurement-Based Admission Control for VBR Video Traffic in Wireless Multimedia Home Networks

An On-Line Measurement-Based Admission Control for VBR Video Traffic in Wireless Multimedia Home Networks

Common Radio Resource Management Strategies for Quality of Service Support in Heterogeneous Wireless Networks

Real-time VP bandwidth control for long-range-dependent traffic

Contact Info

Product

Resources

About