Traffic Handling in AQUILA QoS IP Network

Management of Multimedia Networks and Services

Santos

et al. 2003

Abstract. We propose a lightweight traffic admission control scheme based on on-line monitoring which ensures multimedia services quality both intra-domain and end-to-end. The AC strategy is distributed, service-oriented and allows to control QoS and SLS without adding complexity to the network core. For each service class, AC decisions are driven by rate-based SLS control rules and QoS parameters control rules, defined and parameterized according to each service characteristics. These rules are essentially based on systematic on-line measurements of relevant QoS and performance parameters. Thus, from a practical perspective, we discuss and evaluate methodologies and mechanisms for parameter estimation. The AC criteria is evaluated as regards its ability to ensure service commitments while achieving high network utilization. The results show that the proposed model provides a good compromise between simplicity, service level guarantee and network usage, even for services with strict QoS requirements.

Section: Definition Of Service Classes and Slsmentioning

confidence: 99%

Managing Services Quality through Admission Control and Active Monitoring

Management of Multimedia Networks and Services

Santos

et al. 2003

“…Most of the criteria suggest distinct classes for UDP and TCP traffic so that non-reactive and reactive applications do not compete for the same resources. Some go further suggesting that the duration of flows, the transmission rate and packet size characteristics should also be considered [9]. A classification method based on QoS application requirements such as delay or loss sensitivity is also proposed [10].…”

Section: Traffic Classification Criterionmentioning

confidence: 99%

Long-Range Dependence of Internet Traffic Aggregates

Silva

NETWORKING 2002: Networking Technologies, Services, and Protocols; Performance of Computer and Communication Networks; Mobile A

et al. 2002

Abstract. This paper studies and discusses the presence of LRD in network traffic after classifying flows into traffic aggregates. Following DiffServ architecture principles, generic QoS application requirements and the transport protocol in use, a classification criterion of Internet traffic is established. Using fractal theory, the resulting traffic classes are analysed. The Hurst parameter is estimated and used as a measure of traffic burstiness and LRD in each traffic class. The traffic volume per class and per interface is also measured. The study uses real traffic traces collected at a University of Minho major backbone router in different periods of network activity.

“…3) AC Decision Algorithms: In any AC strategy the admission criterion plays a crucial role as regards service guarantees and network efficiency. There are more or less conservative proposals [18], which consider the estimation and control of parameters such as available bandwidth, delay, loss or ECN marks. Most of AC approaches only control the available bandwidth or capacity, comparing it with the flow requested rates.…”

Section: A Model Areasmentioning

confidence: 99%

A distributed admission control model for CoS networks using QoS and SLS monitoring

IEEE International Conference on Communications, 2003. ICC '03.

Santos

et al.

Achieving an admission control strategy for CoS networks covering both intra-domain and end-to-end operation is still an open issue. This paper discusses how AC can be carried out without adding significant complexity to the network control plane and proposes a distributed service-oriented AC model for these networks. The model only involves the network edge nodes leaving the network core unchanged. Ingress nodes perform implicit or explicit service-dependent AC based on both QoS and SLSs utilization metrics, obtained through edge-to-edge online monitoring performed at egress nodes. From an end-to-end perspective, the flow request is used both for AC and available service computation. Relevant aspects of the model interrelated areas and implementation key points are also discussed.