Irena Atov

OPQR-G: algorithm for efficient QoS partition and routing in multiservice IP networks

This paper considers the combined problem of optimal QoS partition and routing (problem QPQR-G) for a QoS framework in which a performance dependent cost function is associated with each network element and the QoS metric is additive (e.g. delay, jitter). This problem has been addressed in the context of unicast connections and multicast trees only. Here we consider the problem for a more general case of a multicommodity flow network. Also, it is assumed that the performance dependent cost functions are non-increasing and are of general integer type. The goal is to determine primary paths between the origin and destination (OD) pairs and QoS partitions on the links so that the overall cost in the network is minimised while all OD pair QoS requirements are satisfied. As the problem is NP-complete, we concentrate on the development of an efficient heuristic algorithm. In addition, two LP-based algorithms were developed, that use the optimisation tool ILOG(TM) CPLEX 7.1 LP for solving the problem OPQR-G. The numerical results obtained for various test network scenarios are very close to the optimal. The problem addressed in this paper provides the basis for the solution of many interesting and practical engineering problems, such as dimensioning and admission control/resource reservation in IP networks that support service differentiation.

Dimensioning Method for Multiservice IP Networks to Satisfy Delay QoS Constraints

In this paper, we address the problem of dimensioning links in a multiservice IP network to satisfy the varying delay (QoS) constraints for different traffic classes. The delay (QoS) performance objectives are viewed in terms of mean delays required for the various traffic classes or in terms of random variations of their delays (e.g., jitter) or a combination of both. The need for such a method arises as a natural consideration after the development and implementation of various technologies that can support traffic classes with different delay requirements in large-scale IP networks (e.g., DiffSery/MPLS).

Design of IP Networks with End-To-End Performance Guarantees

In this paper, we examine the issues that surround IP network design with quality of service (QoS) guarantees and propose a new network design methodology. The proposed network design model takes account of the new QoS technologies (i.e., DiffServ/MPLS) and allows for multiple delay constraints so that guaranteed performance can be achieved for each of the traffic classes. After discussing the most crucial planning issues that must be addressed when QoS mechanisms are used in an IP-based network, a non-linear multicommodity optimisation problem is formulated and heuristics for its approximate solutions are described. The network design model is evaluated in terms of accuracy and scalability for each of the main components that the model employs. The computational results for each of the building blocks demonstrate that realistic size problems can be solved with the proposed method.

Evaluation of FAST TCP in Low-Speed DOCSIS-based Access Networks

There is strong evidence that the efficiency of the Internet is limited by its existing TCP congestion control system. A replacement, FAST, has been shown to improve performance in high-speed networks. In order to achieve widespread acceptance and standardisation, it must also be tested in environments more typical of the existing Internet. This paper experimentally evaluates the performance of FAST over a typical access link, with bandwidths of around 0.5-3 Mbps. Links both using the DOCSIS cable modem medium access control (MAC) protocol and simple low rate links were investigated. It is shown that the random delay introduced by MAC protocol of the cable modem does not appear to interfere significantly with FASTs ability to set the congestion window size to its target. However, the cable modem does appear to introduce consistent additional delays when the link is highly, but not fully, utilised. These unexplained delays mean that a larger congestion window is required, and must be taken into account when setting FASTs parameters, notably the target queue size, alpha.

Capacity provisioning in DiffServ/MPLS networks based on correlated traffic inputs

In this paper, we propose a dimensioning model that takes account of the new technologies that can provide QoS (i.e., DiffServ/MPLS) and allows for multiple delay constraints so that guaranteed performance can be achieved for each of the traffic classes. The proposed model incorporates procedures that allow correlations and burstiness of IP traffic to be effectively modelled. The accuracy of the model has been investigated by means of a simulation study over a range of test cases. The results demonstrate the capability of the model in guaranteeing the end-to-end delay requirements for the traffic classes.

A Mathematical Model for IP over ATM

We consider IP over ATM networking scenario, widely deployed today, where Asynchronous Transfer Mode (ATM) is used as a backbone network to provide high-speed transport for the Internet Protocol (IP) traffic. Telecommunication network carriers and Internet Service Providers (ISPs), that have deployed ATM as their backbone networks, need to model and characterize the IP traffic in order to plan and manage these networks to meet specified performance measures demanded by their customers. This paper addresses the problem of modelling IP traffic that is being transported over links of an ATM network. It provides mathematical models that can be used to take measurement data and translate it into a form that is suitable for various planning and management functions performed by network carriers.

Capacity planning tool for multiservice IP networks

This paper describes a network planning tool that has been developed in order to provide support for network planners who need to dimension next generation IP networks to meet quality of service (QoS) objectives. Specifically, the proposed network planning tool takes account of the new technologies that enable QoS in IP-based networks (i.e., DiffServ/MPLS) and allows for multiple QoS constraints so that guaranteed performance can be achieved for each of the traffic classes. The primary-decisions for the planning tool include determining class-based bandwidth allocations on the links, total link capacities and how traffic of each class is to be routed through the network. Furthermore, the planning tool incorporates traffic characterisation and dimensioning procedures that allow the known burstiness of IP traffic to be effectively modelled. After discussing some of the specific features and algorithms that have been incorporated into the planning methodology, the planning tool is briefly described and the solution to a simple network problem is demonstrated. The simulation results demonstrate the capability of the tool in achieving the required performance levels for the traffic classes.