Search

Raphtory is a platform for building and analysing temporal networks. The library includes methods for creating networks from a variety of data sources; algorithms to explore their structure and evolution; and an extensible GraphQL server for deployment of applications built on top. Raphtory's core engine is built in Rust, for efficiency, with Python interfaces, for ease of use. Raphtory is developed by network scientists, with a background in Physics, Applied Mathematics, Engineering and Computer Science, for use across academia and industry.

Gab is an online social network often associated with the alt-right political movement and users barred from other networks. It presents an interesting opportunity for research because near-complete data is available from day one of the network's creation. In this paper, we investigate the evolution of the user interaction graph, that is the graph where a link represents a user interacting with another user at a given time. We view this graph both at different times and at different timescales. The latter is achieved by using sliding windows on the graph which gives a novel perspective on social network data. The Gab network is relatively slowly growing over the period of months but subject to large bursts of arrivals over hours and days. We identify plausible events that are of interest to the Gab community associated with the most obvious such bursts. The network is characterised by interactions between `strangers' rather than by reinforcing links between `friends'. Gab usage follows the diurnal cycle of the predominantly US and Europe based users. At off-peak hours the Gab interaction network fragments into sub-networks with absolutely no interaction between them. A small group of users are highly influential across larger timescales, but a substantial number of users gain influence for short periods of time. Temporal analysis at different timescales gives new insights above and beyond what could be found on static graphs., 10 pages, 9 figures

Getting good statistical models of traffic on network links is a well-known, often-studied problem. A lot of attention has been given to correlation patterns and flow duration. The distribution of the amount of traffic per unit time is an equally important but less studied problem. We study a large number of traffic traces from many different networks including academic, commercial and residential networks using state-of-the-art statistical techniques. We show that traffic obeys the log-normal distribution which is a better fit than the Gaussian distribution commonly claimed in the literature. We also investigate an alternative heavy-tailed distribution (the Weibull) and show that its performance is better than Gaussian but worse than log-normal. We examine anomalous traces which exhibit a poor fit for all distributions tried and show that this is often due to traffic outages or links that hit maximum capacity. We demonstrate that the data we look at is stationary if we consider samples of 15- minute long or even 1-hour long. This gives confidence that we can use the distributions for estimation and modelling purposes. We demonstrate the utility of our findings in two contexts: predicting that the proportion of time traffic will exceed a given level (for service level agreement or link capacity estimation) and predicting 95th percentile pricing. We also show that the log-normal distribution is a better predictor than Gaussian or Weibull distributions in both contexts.

Temporal graphs capture the development of relationships within data throughout time. This model fits naturally within a streaming architecture, where new events can be inserted directly into the graph upon arrival from a data source and be compared to related entities or historical state. However, the vast majority of graph processing systems only consider traditional graph analysis on static data, with some outliers supporting batched updating and temporal analysis across graph snapshots. In this work we define a temporal graph model which can be updated via event streams and discuss the challenges of distribution and graph maintenance. To solve these challenges, we introduce Raphtory, a distributed temporal graph management system which maintains the full graph history in memory, leveraging this to insert streamed events directly into the model without batching or centralised ordering. Raphtory additionally provides an API to perform both approximative analysis on the most up-to-date version of the graph, as well as temporal analysis throughout its full history; executed in parallel with ingestion.

Alternative paths in a network play an important role in its functionality as they can maintain the information flow under node/link failures. In this paper we explore the navigation of a network taking into account the alternative paths and in particular how can we describe this navigation in a concise way. Our approach is to simplify the network by aggregating into groups the nodes that do not contribute to alternative paths. We refer to these groups as super-nodes, and describe the post-aggregation network with super-nodes as the skeleton network. We present a method to describe with the least amount of information the paths in the super-nodes and skeleton network. Applying our method to several real networks we observed that there is scaling behaviour between the information required to describe all the paths in a network and the minimal information to describe the paths of its skeleton. We show how from this scaling we can evaluate the information of the paths for large networks with less computational cost.

Motion sensors embedded in wearable and mobile devices allow for dynamic selection of sensor streams and sampling rates, enabling several applications, such as power management and data-sharing control. While deep neural networks (DNNs) achieve competitive accuracy in sensor data classification, DNNs generally process incoming data from a fixed set of sensors with a fixed sampling rate, and changes in the dimensions of their inputs cause considerable accuracy loss, unnecessary computations, or failure in operation. We introduce a dimension-adaptive pooling (DAP) layer that makes DNNs flexible and more robust to changes in sensor availability and in sampling rate. DAP operates on convolutional filter maps of variable dimensions and produces an input of fixed dimensions suitable for feedforward and recurrent layers. We also propose a dimension-adaptive training (DAT) procedure for enabling DNNs that use DAP to better generalize over the set of feasible data dimensions at inference time. DAT comprises the random selection of dimensions during the forward passes and optimization with accumulated gradients of several backward passes. Combining DAP and DAT, we show how to transform non-adaptive DNNs into a Dimension-Adaptive Neural Architecture (DANA), while keeping the same number of parameters. Compared to existing approaches, our solution provides better classification accuracy over the range of possible data dimensions at inference time and does not require up-sampling or imputation, thus reducing unnecessary computations. Experiments on seven datasets (four benchmark real-world datasets for human activity recognition and three synthetic datasets) show that DANA prevents significant losses in classification accuracy of the state-of-the-art DNNs and, compared to baselines, it better captures correlated patterns in sensor data under dynamic sensor availability and varying sampling rates., Comment: Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., Vol. 5, No. 3, Article 120. Publication date: September 2021

Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform sensor data before sharing them with applications running on users' devices. These transformations aim at eliminating patterns that can be used for user re-identification or for inferring potentially sensitive activities, while introducing a minor utility loss for the target application (or task). We show that, on gesture and activity recognition tasks, we can prevent inference of potentially sensitive activities while keeping the reduction in recognition accuracy of non-sensitive activities to less than 5 percentage points. We also show that we can reduce the accuracy of user re-identification and of the potential inference of gender to the level of a random guess, while keeping the accuracy of activity recognition comparable to that obtained on the original data., Accepted to appear in Pervasive and Mobile computing (PMC) Journal, Elsevier

TCP remains the dominant transport protocol for Internet traffic. It is usually considered to have its sending rate covered by a sliding window congestion control mechanism. However, in addition to this normal congestion control, a number of other mechanisms limit TCP throughput. This paper analyses the extent to which network, host and application settings define flow throughput over time and across autonomous systems. Our study draws on data from a longitudinal study spanning five years of passive traces collected from a single transit link. Mechanisms for this include limiting by application, interference with the TCP window control mechanism and artificial limitations on maximum window sizes by the operating system. This paper uses a large data set to assess the impact of each mechanism. We conclude that more than half of all heavy-hitter inbound traffic remains throttled by constraints beyond network capacity. For this data set, TCP congestion control is no longer the dominant mechanism that moderates throughput.

Cloud computing has revolutionized service delivery by providing on-demand invocation and elasticity. To reap these benefits, computation has been displaced from client devices and into data centers. This partial centralization is undesirable for applications that have stringent locality requirements, e.g., low latency. This problem could be addressed with large numbers of smaller cloud resources closer to users. However, as cloud computing diffuses from within data centers and into the network, there will be a need for cloud resource allocation algorithms that operate on resource-constrained computational units that serve localized subsets of customers. In this paper, we present a mechanism for service provisioning in distributed clouds where applications compete for resources. The mechanism operates by enabling execution zones to assign resources based on Vickrey auctions and provides high-quality probabilistic models that applications can use to predict the outcomes of such auctions. This allows applications to use knowledge of the locality distribution of their clients to accurately select the number of bids to be sent to each execution zone and their value. The proposed mechanism is highly scalable, efficient, and validated by extensive simulations.

Getting good statistical models of traffic on network links is a well-known, often-studied problem. A lot of attention has been given to correlation patterns and flow duration. The distribution of the amount of traffic per unit time is an equally important but less studied problem. We study a large number of traffic traces from many different networks including academic, commercial and residential networks using state-of-the-art statistical techniques. We show that the log-normal distribution is a better fit than the Gaussian distribution commonly claimed in the literature. We also investigate a second heavy-tailed distribution (the Weibull) and show that its performance is better than Gaussian but worse than log-normal. We examine anomalous traces which are a poor fit for all distributions tried and show that this is often due to traffic outages or links that hit maximum capacity. We demonstrate the utility of the log-normal distribution in two contexts: predicting the proportion of time traffic will exceed a given level (for service level agreement or link capacity estimation) and predicting 95th percentile pricing. We also show the log-normal distribution is a better predictor than Gaussian or Weibull distributions., Accepted for INFOCOM 2019

Discriminating between competing explanatory models as to which is more likely responsible for the growth of a network is a problem of fundamental importance for network science. The rules governing this growth are attributed to mechanisms such as preferential attachment and triangle closure, with a wealth of explanatory models based on these. These models are deliberately simple, commonly with the network growing according to a constant mechanism for its lifetime, to allow for analytical results. We use a likelihood-based framework on artificial data where the network model changes at a known point in time and demonstrate that we can recover the change point from analysis of the network. We then use real datasets and demonstrate how our framework can show the changing importance of network growth mechanisms over time.

Remembering our day-to-day social interactions is challenging even if you aren't a blue memory challenged fish. The ability to automatically detect and remember these types of interactions is not only beneficial for individuals interested in their behavior in crowded situations, but also of interest to those who analyze crowd behavior. Currently, detecting social interactions is often performed using a variety of methods including ethnographic studies, computer vision techniques and manual annotation-based data analysis. However, mobile phones offer easier means for data collection that is easy to analyze and can preserve the user's privacy. In this work, we present a system for detecting stationary social interactions inside crowds, leveraging multi-modal mobile sensing data such as Bluetooth Smart (BLE), accelerometer and gyroscope. To inform the development of such system, we conducted a study with 24 participants, where we asked them to socialize with each other for 45 minutes. We built a machine learning system based on gradient-boosted trees that predicts both 1:1 and group interactions with 77.8% precision and 86.5% recall, a 30.2% performance increase compared to a proximity-based approach. By utilizing a community detection-based method, we further detected the various group formation that exist within the crowd. Using mobile phone sensors already carried by the majority of people in a crowd makes our approach particularly well suited to real-life analysis of crowd behavior and influence strategies., 21 pages, 6 figures, conference paper

There is growing concern about how personal data are used when users grant applications direct access to the sensors of their mobile devices. In fact, high resolution temporal data generated by motion sensors reflect directly the activities of a user and indirectly physical and demographic attributes. In this paper, we propose a feature learning architecture for mobile devices that provides flexible and negotiable privacy-preserving sensor data transmission by appropriately transforming raw sensor data. The objective is to move from the current binary setting of granting or not permission to an application, toward a model that allows users to grant each application permission over a limited range of inferences according to the provided services. The internal structure of each component of the proposed architecture can be flexibly changed and the trade-off between privacy and utility can be negotiated between the constraints of the user and the underlying application. We validated the proposed architecture in an activity recognition application using two real-world datasets, with the objective of recognizing an activity without disclosing gender as an example of private information. Results show that the proposed framework maintains the usefulness of the transformed data for activity recognition, with an average loss of only around three percentage points, while reducing the possibility of gender classification to around 50\%, the target random guess, from more than 90\% when using raw sensor data. We also present and distribute MotionSense, a new dataset for activity and attribute recognition collected from motion sensors., 6 pages

Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions. Raw data streams from motion sensors embedded in portable and wearable devices may reveal private information about users without their awareness. For example, motion data might disclose the weight or gender of a user, or enable their re-identification. To address this problem, we propose an on-device transformation of sensor data to be shared for specific applications, such as monitoring selected daily activities, without revealing information that enables user identification. We formulate the anonymization problem using an information-theoretic approach and propose a new multi-objective loss function for training deep autoencoders. This loss function helps minimizing user-identity information as well as data distortion to preserve the application-specific utility. The training process regulates the encoder to disregard user-identifiable patterns and tunes the decoder to shape the output independently of users in the training set. The trained autoencoder can be deployed on a mobile or wearable device to anonymize sensor data even for users who are not included in the training dataset. Data from 24 users transformed by the proposed anonymizing autoencoder lead to a promising trade-off between utility and privacy, with an accuracy for activity recognition above 92% and an accuracy for user identification below 7%., Comment: 10 pages

This paper addresses the problem of provisioning management/monitoring nodes within highly dynamic network environments, particularly virtual networks. In a network, where nodes and links may be spontaneously created and destroyed (perhaps rapidly) there is a need for stable and responsive management and monitoring, which does not create a large load (in terms of traffic or processing) for the system. A subset of nodes has to be chosen for management/monitoring, each of which will manage a subset of the nodes in the network. A new, simple, and locally optimal greedy algorithm called Pressure is provided for choice of node position to minimize traffic. This algorithm is combined with a system for predicting the lifespan of nodes, and a tunable parameter is also given so that a system operator could express a preference for elected nodes to be chosen to reduce traffic, to be "stable,” or some compromise between these positions. The combined algorithm called PressureTime is lightweight and could be run in a distributed manner. The resulting algorithms are tested both in simulation and in a testbed environment of virtual routers. They perform well, both at reducing traffic and at choosing long lifespan nodes.

Multi-user video conferencing is a ubiquitous technology. Increasingly end-hosts in a conference are assisted by cloud-based servers that improve the quality of experience for end users. This paper evaluates the impact of strategies for placement of such servers on user experience and deployment cost. We consider scenarios based upon the Amazon EC2 infrastructure as well as future scenarios in which cloud instances can be located at a larger number of possible sites across the planet. We compare a number of possible strategies for choosing which cloud locations should host services and how traffic should route through them. Our study is driven by real data to create demand scenarios with realistic geographical user distributions and diurnal behaviour. We conclude that on the EC2 infrastructure a well chosen static selection of servers performs well but as more cloud locations are available a dynamic choice of servers becomes important.

An increasing number of sensors on mobile, Internet of things (IoT), and wearable devices generate time-series measurements of physical activities. Though access to the sensory data is critical to the success of many beneficial applications such as health monitoring or activity recognition, a wide range of potentially sensitive information about the individuals can also be discovered through access to sensory data and this cannot easily be protected using traditional privacy approaches. In this paper, we propose a privacy-preserving sensing framework for managing access to time-series data in order to provide utility while protecting individuals' privacy. We introduce Replacement AutoEncoder, a novel algorithm which learns how to transform discriminative features of data that correspond to sensitive inferences, into some features that have been more observed in non-sensitive inferences, to protect users' privacy. This efficiency is achieved by defining a user-customized objective function for deep autoencoders. Our replacement method will not only eliminate the possibility of recognizing sensitive inferences, it also eliminates the possibility of detecting the occurrence of them. That is the main weakness of other approaches such as filtering or randomization. We evaluate the efficacy of the algorithm with an activity recognition task in a multi-sensing environment using extensive experiments on three benchmark datasets. We show that it can retain the recognition accuracy of state-of-the-art techniques while simultaneously preserving the privacy of sensitive information. Finally, we utilize the GANs for detecting the occurrence of replacement, after releasing data, and show that this can be done only if the adversarial network is trained on the users' original data., Comment: 12 pages, 11 figures

Researchers have examined crowd behavior in the past by employing a variety of methods including ethnographic studies, computer vision techniques and manual annotation based data analysis. However, because of the resources to collect, process and analyze data, it remains difficult to obtain large data sets for study. In an attempt to alleviate this problem, researchers have recently used mobile sensing, however this technique is currently only able to detect either stationary or moving crowds with questionable accuracy. In this work we present a system for detecting stationary interactions inside crowds using the Received Signal Strength Indicator of Bluetooth Smart (BLE) sensor, combined with the Motion Activity of each device. By utilizing Apple's iBeacon™ implementation of Bluetooth Smart, we are able to detect the proximity of users carrying a smartphone in their pocket. We then use an algorithm based on graph theory to predict interactions inside the crowd and verify our findings using video footage as ground truth. Our approach is particularly beneficial to the design and implementation of crowd behavior analytics, design of influence strategies, and algorithms for crowd reconfiguration.

This paper proposes a new decentralised multi-channel tree building protocol with a centralised controller for the Internet of Things. The protocol alleviates the effect of interference which results in improved network efficiency and stability, and link reliability. The proposal takes into account all available channels to utilise the spectrum and aims to use the spectrum efficiently by transmitting on several channels. The protocol detects which channels suffer interference and changes away from those channels. The algorithm for channel selection is a two-hop colouring protocol that reduces the chances of nearby nodes to transmit on the same channel. All nodes are battery operated except for the low power border router (LPBR). This enables a centralised channel switching process at the LPBR. The protocol is built based on the routing protocol for low power and lossy networks (RPL). In its initial phase, the protocol uses RPL's standard topology formation to create an initial working topology and then seeks to improve this topology by switching channels. The implementation and evaluation of the protocol is performed using the Contiki framework. The experimental results demonstrate an increased resilience to interference and significantly higher throughput making better use of the total available spectrum and link stability.

This paper deals with the problem of assessing probabilistic models that represent the evolution of a target graph. Such models have long been a topic of interest for a number of networks, especially communications networks. The solution developed in this paper gives a rigorous way to calculate the likelihood of the observed graph evolution having arisen from a wide variety of hypothesized models encompassing many already present in the literature. The framework is shown to recover parameters from artificial data and is tested on real data sets from Facebook and from emails from the company Enron.

This paper describes a robust architecture for high speed serial links for embedded SoC applications, implemented to satisfy the 1.5 Gb/s and 3 Gb/s Serial-ATA PHY standards. To meet the primary design requirements of a sub-system that is very tolerant of device variability and is easy to port to smaller nanometre CMOS technologies, a minimum of precision analog functions are used. All digital functions are implemented in rail-to-rail CMOS with maximum use of synthesized library cells. A single fixed frequency low-jitter PLL serves the transmit and receive paths in both modes so that tracking and lock time issues are eliminated. A new oversampling CDR with a simple feed-forward error correction scheme is proposed which relaxes the requirements for the analog front-end as well as for the received signal quality. Measurements show that the error corrector can almost double the tolerance to incoming jitter and to DC offsets in the analog front-end. The design occupies less than 0.4 mm2 in 90 nm CMOS and consumes 75 mW.

We present a system for streaming live entertainment content over the Internet originating from a single source to a scalable number of consumers without resorting to centralised or provider- provisioned resources. The system creates a peer-to-peer overlay network, which attempts to optimise use of existing capacity to ensure quality of service, delivering low start-up delay and lag in playout of the live content. There are three main aspects of our solution. Firstly, a swarming mechanism that constructs an overlay topology for minimising propagation delays from the source to end consumers. Secondly, a distributed overlay anycast system that uses a location-based search algorithm for peers to quickly find the closest peers in a given stream. Finally, a novel incentives mechanism that encourages peers to donate capacity even when the user is not actively consuming content., Comment: 11 pages, 6 figures

Existing methods for traffic resilience at the network and transport layers typically work in isolation, often resorting to inference in fault detection and recovery respectively. This both duplicates functionality across layers, eroding efficiency, and leads to protracted recovery cycles, affecting responsiveness. Such misalignment is particularly at odds with the unprecedented concentration of traffic in data-centers, in which network and hosts are managed in unison. This paper advocates instead a cross-layer approach to traffic resilience. The proposed architecture, INFLEX, builds on the abstractions provided by software-defined networking (SDN) to maintain multiple virtual forwarding planes which the network assigns to flows. In case of path failure, transport protocols pro-actively request to switch plane in a manner which is unilaterally deployable by an edge domain, providing scalable end-to-end forwarding path resilience.

This paper considers fundamental measurements which drive TCP flows: throughput, RTT and loss. It is clear that throughput is, in some sense, a function of both RTT and loss. In their seminal paper Padyhe et al [1] begin with a mathematical model of the TCP sliding window evolution process and come up with an equation showing that TCP throughput is (roughly) proportional to 1/RTT√p where p is the probability of packet loss. Their equation is shown to be consistent with data gathered on several links. This paper takes the opposite approach and analyses a large number of packet traces from well-known sources in order to create a data-driven estimate of the functions which relate TCP, loss and RTT. Regression analysis is used to fit models to connect the quantities. The fitted models show different behaviour from that expected in [1].

Spectral efficiency is a key design issue for all wireless communication systems. Orthogonal frequency division multiplexing (OFDM) is a very well-known technique for efficient data transmission over many carriers overlapped in frequency. Recently, several papers have appeared which describe spectrally efficient variations of multi-carrier systems where the condition of orthogonality is dropped. Proposed techniques suffer from two weaknesses: Firstly, the complexity of generating the signal is increased. Secondly, the signal detection is computationally demanding. Known methods suffer either unusably high complexity or high error rates because of the inter-carrier interference. This work addresses both problems by proposing new transmitter and receiver arch itectures whose design is based on using the simplification that a rational Spectrally Efficient Frequency Division Multiplexing (SEFDM) system can be treated as a set of overlapped and interleaving OFDM systems. The efficacy of the proposed designs is shown through detailed simulation of sys tems with different signal types and carrier dimensions. The decoder is heuristic but in practice produces very good results which are close to the theoretical best performance in a variety of settings. The system is able to produce efficiency gains of up to 20% with negligible impact on the required signal to noise ratio., 24 pages, 6 figures

The production of a large-scale monitoring system for a high-speed network leads to a number of challenges. These challenges are not purely techinical but also socio-political and legal. The number of stakeholders in a such a monitoring activity is large including the network operators, the users, the equipment manufacturers and of course the monitoring researchers. The MASTS project (Measurement at All Scales in Time and Space) was created to instrument the high-speed JANET Lightpath network, and has been extended to incorporate other paths supported by JANET(UK). Challenges the project has faced have included: simple access to the network; legal issues involved in the storage and dissemination of the captured information, which may be personal; the volume of data captured and the rate at which this data appears at store. To this end the MASTS system will have established four monitoring points each capturing packets on a high speed link. Traffic header data will be continuously collected, anonymised, indexed, stored and made available to the research community. A legal framework for the capture and storage of network measurement data has been developed which allows the anonymised IP traces to be used for research pur poses., 21 pages, 4 figures

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., Presented at ACM/SIMPLEX '09 Workshop, ACM/SIMPLEX '09 Proceedings of the 1st Annual Workshop on Simplifying Complex Network for Practitioners 2009

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., Comment: Published in INFOCOM NetSciCom Workshop 2009. http://dl.acm.org/citation.cfm?id=1719896

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., Comment: Paper presented at IEEE/ICC conference 2010

In this paper we present the \emph{Distributed Overlay Anycast Table}, a structured overlay that implements application-layer anycast, allowing the discovery of the closest host that is a member of a given group. One application is in locality-aware peer-to-peer networks, where peers need to discover low-latency peers participating in the distribution of a particular file or stream. The DOAT makes use of network delay coordinates and a space filling curve to achieve locality-aware routing across the overlay, and Bloom filters to aggregate group identifiers. The solution is designed to optimise both accuracy and query time, which are essential for real-time applications. We simulated DOAT using both random and realistic node distributions. The results show that accuracy is high and query time is low., Comment: 7 pages, 4 figures

The increasing demand for efficient content distribution using the Internet has fuelled the deployment of varied techniques such as peer-to-peer overlays, content distribution networks and distributed caching systems. These have had considerable impact on ISP infrastructure demand, motivating the development of protocols that enable mutually beneficial cooperative outcomes. In this paper we propose a parameterised cooperation utility that can be used to study the tradeoff between the benefit that an overlay obtains from the ISPs that carry its traffic and the costs that it imposes on them. With this utility, we find a closed-form expression for the optimal resource allocation given a particular cooperation tradeoff, subject to both minimal benefit and maximal cost constraints. Since the model is implementation-independent and has very modest computational demands, it is ideal for large scale simulation. We explore the properties of the proposed model through simulation in both a simple illustrative scenario and a more complete one based on network datasets. The results obtained from the model are shown to be consistent with those of measurement-based studies of overlay-ISP collaboration.

The popularity of video sharing over the Internet has increased significantly. High traffic generated by such applications at the source can be better distributed using a peer-to-peer (P2P) overlay. Unlike most P2P systems, LiveShift combines both live and on-demand video streaming — while video is transmitted through the peer-to-peer network in a live fashion, all peers participate in distributed storage. This adds the ability to replay time-shifted streams from other peers in a distributed and scalable manner. This paper describes an adaptive fully-distributed mesh-pull protocol that supports the envisioned use case and a set of policies that enable efficient usage of resources, discussing interesting trade-offs encountered. User-focused evaluation results, including both channel switching and time shifting behavior, show that the proposed system provides good quality of experience for most users, in terms of infrequent stalling, low playback lag, and a small proportion of skipped blocks in all the scenarios studied, even in presence of churn.

Networking Named Content (NNC) was recently proposed as a new networking paradigm to realise Content Centric Networks (CCNs). The new paradigm changes much about the current Internet, from security and content naming and resolution, to caching at routers, and new flow models. In this paper, we study the caching part of the proposed networking paradigm in isolation from the rest of the suggested features. In CCNs, every router caches packets of content and reuses those that are still in the cache, when subsequently requested. It is this caching feature of CCNs that we model and evaluate in this paper. Our modelling proceeds both analytically and by simulation. Initially, we develop a mathematical model for a single router, based on continuous time Markov-chains, which assesses the proportion of time a given piece of content is cached. This model is extended to multiple routers with some simple approximations. The mathematical model is complemented by simulations which look at the caching dynamics, at the packet-level, in isolation from the rest of the flow.

There has long been a need for a robust and reliable system which distributes traffic across multiple paths. In particular such a system must rarely reorder packets, must not require per-flow state, must cope with different paths having different bandwidths and must be self-tuning in a variety of network contexts. PREFLEX, proposed herein, uses estimates of loss rate to balance congestion. This paper describes a method of automatically adjusting how PREFLEX will split traffic in order to balance loss across multiple paths in a variety of network conditions. Equations are derived for the automatic tuning of the time scale and traffic split at a decision point. The algorithms described allow the load balancer to self-tune to network conditions. The calculations are simple and do not place a large burden on a router which would implement the algorithm. The algorithm is evaluated by simulation using ns-3 and is shown to perform well under a variety of circumstances. The resulting adaptive, end-to-end traffic balancing architecture provides the necessary framework to meet the increasing demands of users while simultaneously offering edge networks more fine-grained control at far shorter timescales.

This paper takes a critical look at the usefulness of power law models of the Internet. The twin focuses of the paper are Internet traffic and topology generation. The aim of the paper is twofold. Firstly it summarises the state of the art in power law modelling particularly giving attention to existing open research questions. Secondly it provides insight into the failings of such models and where progress needs to be made for power law research to feed through to actual improvements in network performance., To appear Computer Communications

Although direct reciprocity (Tit-for-Tat )c ontribu- tion systems have been successful in reducing freeloading in peer- to-peer overlays, it has been shown that, unless the contribution network is dense, they tend to be slow (or may even fail) to converge (1). On the other hand, current indirect reciprocity mechanisms based on reputation systems tend to be susceptible to sybil attacks, peer slander and whitewashing. In this paper we present PledgeRoute, an accounting mech- anism for peer contributions that is based on social capital. This mechanism allows peers to contribute resources to one set of peers and use this contribution to obtain services from a different set of peers, at a different time. PledgeRoute is completely decentralised, can be implemented in both structured and unstructured peer-to-peer systems, and it is resistant to the three kinds of attacks mentioned above. To achieve this, we model contribution transitivity as a routing problem in the contribution network of the peer-to-peer overlay, and we present arguments for the routing behaviour and the sybilproofness of our contribution transfer procedures on this basis. Additionally, we present mechanisms for the seeding of the contribution network, and a combination of incentive mechanisms and reciprocation policies that motivate peers to adhere to the protocol and maximise their service contributions to the overlay.

Peer-to-peer networks providing QoS-enabled services are sensitive to hidden action situations, where the actions of a server peer are hidden from the peers who receive services from it. This is because server peers can choose to strategically minimize their effort, and client peers may be unable to distinguish between cases where the server exerted insufficient effort and cases where the server kept its advertised effort levels but the end-to-end conditions in the network were sufficiently adverse. We propose a principal-agent model for hidden action that gives server peers sufficient incentives to meet their advertised effort levels, without client peers having to decide for each transaction whether the outcome was due to server behavior or network conditions. This allows peers to draft contracts that provide incentives for truthful revelation of QoS capabilities, and to have predictable transaction quality. We then exemplify the model for the case of a mesh-based, pull-oriented streaming system with low delay requirements. For this case, we show how to estimate the model parameters a function of the prevailing network conditions, and how to enforce contract fulfillment through a reciprocative strategy.

The distribution of flow sizes is a quantity of interest fundamental to traffic engineering and network modelling and only likely to become more important in the future. The recovery of the flow-length distribution from (sampled) packet data is referred to as flow-inversion. Traditional packet sampling methods cause distortions in a recovered distribution of flow-length. We propose an improved method for inverting data sampled using the technique known as sample-and-hold. We show that the technique improves upon existing inversion techniques illustrated using both real and artificial data sets. The technique described may have applications to other inversion problems.

This paper describes a framework for analysing matches in multiple data sets. The framework described is quite general and can be applied to a variety of problems where matches are to be found in data surveyed at a number of locations (or at a single location over a number of days). As an example, the framework is applied to the problem of false matches in licence plate survey data. The specific problem addressed is that of estimating how many vehicles were genuinely sighted at every one of a number of survey points when there is a possibility of accidentally confusing two vehicles due to the nature of the survey undertaken. In this paper, a method for representing the possible "types of match" is outlined using set theory. The phrase "types of match" will be defined and formalised in this paper. A method for enumerating the set of all types of match over n survey sites, is described. The method is applied to the problem of correcting survey data for false matches using a simple probabalistic method. An algorithm is developed for correcting false matches over multiple survey sites and its use is demonstrated with simulation results., 13 pages, 1 figure

This paper examines a discrete-time queuing system with applications to telecommunications traffic. The arrival process is a particular Markov modulated process which belongs to the class of discrete batched Markovian arrival processes. The server process is a single server deterministic queue. A closed form exact solution is given for the expected queue length and delay. A simple system of equations is given for the probability of the queue exceeding a given length., Comment: to appear Performance Evaluation

This paper describes a model for generating time series which exhibit the statistical phenomenon known as long-range dependence (LRD). A Markov Modulated Process based upon an infinite Markov chain is described. The work described is motivated by applications in telecommunications where LRD is a known property of time-series measured on the internet. The process can generate a time series exhibiting LRD with known parameters and is particularly suitable for modelling internet traffic since the time series is in terms of ones and zeros which can be interpreted as data packets and inter-packet gaps. The method is extremely simple computationally and analytically and could prove more tractable than other methods described in the literature, 8 pages, 2 figures

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 is an expanded version of a paper presented at the 2008 UK Performance Engineering Workshop

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., Comment: This is an extended version of the conference paper http://arxiv.org/abs/0910.0144