Miguel Rio

This paper criticises the notion that long-range dependence is an important contributor to the queuing behaviour of real Internet traffic. The idea is questioned in two different ways. Firstly, a class of models used to simulate Internet traffic is shown to have important theoretical flaws. It is shown that this behaviour is inconsistent with the behaviour of real traffic traces. Secondly, the notion that long-range correlations significantly affects the queuing performance of traffic is investigated by destroying those correlations in real traffic traces (by reordering). It is shown that the longer ranges of correlations are not important except in one case with an extremely high load.

In this paper, we propose a mechanism for packet marking called Probabilistic Congestion Notification (PCN). This scheme makes use of the 1-bit Explicit Congestion Notification (ECN) field in the Internet Protocol (IP) header. It allows the source to estimate the exact level of congestion at each intermediate queue. By knowing this, the source could take avoiding action either by adapting its sending rate or by using alternate routes. The estimation mechanism makes use of time series analysis both to improve the quality of the congestion estimation and to predict, ahead of time, the congestion level which subsequent packets will encounter. The proposed protocol is tested in ns-2 simulator using a background of real Internet traffic traces. Results show that the methods can successfully calculate the congestion at any queue along the path with low error levels.

This paper is concerned with the effect of overlay network topology on the performance of live streaming peer-to-peer systems. The paper focuses on the evaluation of topologies which are aware of the delays experienced between different peers on the network. Metrics are defined which assess the topologies in terms of delay, bandwidth usage and resilience to peer drop-out. Several topology creation algorithms are tested and the metrics are measured in a simple simulation testbed. This gives an assessment of the type of gains which might be expected from locality awareness in peer-to-peer networks.

This paper presents a statistically sound method for using likelihood to assess potential models of network evolution. The method is tested on data from five real networks. Data from the internet autonomous system network, from two photo sharing sites and from a co-authorship network are tested using this framework.

Many researchers have hypothesised models which explain the evolution of the topology of a target network. The framework described in this paper gives the likelihood that the target network arose from the hypothesised model. This allows rival hypothesised models to be compared for their ability to explain the target network. A null model (of random evolution) is proposed as a baseline for comparison. The framework also considers models made from linear combinations of model components. A method is given for the automatic optimisation of component weights. The framework is tested on simulated networks with known parameters and also on real data.

This paper proposes an adaptation of two network size estimation methods: random tour and gossip-based aggregation to suit master/slave mobile ad hoc networks. We show that it is feasible to accurately estimate the size of ad hoc networks when topology changes due to mobility using both methods. The algorithms were modified to account for the specific constraints of master/slave ad hoc networks and the results show that the proposed modifications perform better on these networks than the original protocols. Each of the two algorithms presents strengths and weaknesses and these are outlined in this paper.

This paper criticises the notion that long-range dependence is an important contributor to the queuing behaviour of real Internet traffic. The idea is questioned in two different ways. Firstly, a class of models used to simulate Internet traffic is shown to have important theoretical flaws. It is shown that this behaviour is inconsistent with the behaviour of real traffic traces. Secondly, the notion that long-range correlations significantly affects the queuing performance of traffic is investigated by destroying those correlations in real traffic traces (by reordering). It is shown that the longer ranges of correlations are not important except in one case with an extremely high load.