Dynamic Neural-Based Buffer Management for Queuing Systems With Self-Similar Characteristics

Yousefi'zadeh, H.; Jonckheere, Edmond

doi:10.1109/tnn.2005.853417

Cited by 26 publications

(7 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many models have been developed to characterize selfsimilar traffic or generate self-similar traffic traces (e.g., [12], [17]). Among the developed models, Fractional Brownian Motion (FBM) is an efficient and widely used way for modelling and generating self-similar traffic and is thus adopted in this paper.…”

Section: Queueing Systems With Self-similar Trafficmentioning

confidence: 99%

A Comprehensive Analytical Model for Weighted Fair Queuing under Multi-Class Self-Similar Traffic

Jin

Min

Wang

2009

2009 IEEE International Conference on Communications

View full text Add to dashboard Cite

Weighted Fair Queueing (WFQ) is a practical scheduling discipline for supporting differentiated Quality-ofService (QoS) in computer networks and communication systems. Analytical models are important tools for system performance evaluation and resource optimization. However, there is not any comprehensive model reported in the open literature for analytically investigating the performance behaviors of WFQ subject to multiple self-similar traffic flows. To fill this gap, this paper develops such a model and derives the upper bounds for the distributions of several important QoS performance metrics including queue length, packet delay and loss of traffic flows in the WFQ system. The comparison between analytical and simulation results using the traffic parameters obtained from real-world MPEG frame traces validates the accuracy of the developed model which can be used for investigating the performance behavior of WFQ systems with multi-class selfsimilar traffic under realistic working conditions.

show abstract

Section: Queueing Systems With Self-similar Trafficmentioning

confidence: 99%

A Comprehensive Analytical Model for Weighted Fair Queuing under Multi-Class Self-Similar Traffic

Jin

Min

Wang

2009

2009 IEEE International Conference on Communications

View full text Add to dashboard Cite

show abstract

“…The seminal work of Leland et al [8] has triggered an explosion of research on traffic self-similarity (e.g., [14,26,29]), which has been discovered as a ubiquitous phenomenon in modern communication networks and multimedia systems, including wired local-area networks [8], wide-area networks [21], wireless and mobile networks [9,22], World Wide Web [5], and Variable-Bit-Rate (VBR) video systems [2]. So far, many models have been developed to characterize traffic self-similarity or generate self-similar traffic traces.…”

Section: Modeling Self-similar Trafficmentioning

confidence: 99%

A heuristic flow-decomposition approach for generalized processor sharing under self-similar traffic

Jin

Min

2008

Journal of Computer and System Sciences

View full text Add to dashboard Cite

The well-known Generalized Processor Sharing (GPS) scheduling principle and its variants have received tremendous research efforts due to their appealing properties of fairness, traffic isolation, and work conservation. Traffic self-similarity is highly detrimental to the performance of scheduling mechanisms and communication networks. This paper proposes a novel and heuristic flow-decomposition approach to performance modeling of the GPS system under self-similar traffic. Based on the comprehensive analysis of the excess service sharing behavior of traffic flows, we decompose the GPS system equivalently into a group of single-server single-queue systems. Extensive simulation experiments are used to validate the correctness of the proposed flowdecomposition approach as well as the analytical performance results.

show abstract

“…Their work has triggered an explosion of research on this subject (e.g., [28][29][30]). Many subsequent studies have further demonstrated traffic self-similarity be a ubiquitous phenomenon in a variety of telecommunication systems [9][10][11][12][13].…”

Section: Self-similar Trafficmentioning

confidence: 99%

Performance analysis of priority scheduling mechanisms under heterogeneous network traffic

Jin¹,

Min²

2007

Journal of Computer and System Sciences

View full text Add to dashboard Cite

Priority scheduling principle plays a crucial role in the Differentiated Services (DiffServ) architecture for the provisioning of Quality-of-Service (QoS) of network-based applications. Analytical modelling and performance evaluation of priority queuing systems have received significant attention and research efforts. However, most existing work has primarily focused on the analysis of priority queuing under either Short Range Dependent (SRD) or Long Range Dependent (LRD) traffic only. Recent studies have shown that realistic traffic reveals heterogeneous nature within modern multi-service networks. With the aim of investigating the impact of heterogeneous traffic on the design and performance of network-based systems, this paper proposes a novel analytical model for priority queuing systems subject to heterogeneous LRD self-similar and SRD Poisson traffic. The key contribution of the paper is to extend the application of the generalized Schilder's theorem (originally a large deviation principle for handling Gaussian processes only) to deal with heterogeneous traffic and further develop the analytical upper and lower bounds of the queue length distributions for individual traffic flows. The validity and accuracy of the model demonstrated through extensive comparisons between analytical bounds and simulation results make it a practical and cost-effective evaluation tool for investigating the performance behaviour of priority queuing systems under heterogeneous traffic with various parameter settings.

show abstract

Dynamic Neural-Based Buffer Management for Queuing Systems With Self-Similar Characteristics

Abstract: Index Terms-Buffer management, fairness, neural network teletraffic forecasting, packet loss, water-filling.

Cited by 26 publications

References 46 publications

A Comprehensive Analytical Model for Weighted Fair Queuing under Multi-Class Self-Similar Traffic

A Comprehensive Analytical Model for Weighted Fair Queuing under Multi-Class Self-Similar Traffic

A heuristic flow-decomposition approach for generalized processor sharing under self-similar traffic

Performance analysis of priority scheduling mechanisms under heterogeneous network traffic

Contact Info

Product

Resources

About