The task of reviewer recommendation is increasingly important, with main techniques utilizing general models of text relevance. However, state of the art (SotA) systems still have relatively high error rates. Two possible reasons for this are: a lack of large datasets and the fact that large language models (LLMs) have not yet been applied. To fill these gaps, we first create a substantial new dataset, in the domain of Internet specification documents; then we introduce the use of LLMs and evaluate their performance. We find that LLMs with prompting can improve on SotA in some cases, but that they are not a cure-all: this task provides a challenging setting for prompt-based methods

An important concept in organisational behaviour is how hierarchy affects the voice of individuals, whereby members of a given organisation exhibit differing power relations based on their hierarchical position. Although there have been prior studies of the relationship between hierarchy and voice, they tend to focus on more qualitative small-scale methods and do not account for structural aspects of the organisation. This paper develops large-scale computational techniques utilising temporal network analysis to measure the effect that organisational hierarchy has on communication patterns throughout an organisation, focusing on the structure of pairwise interactions between individuals. To this end, we focus on one major organisation as a case study --- the Internet Engineering Task Force (IETF) --- a major technical standards development organisation for the Internet. A particularly useful feature of the IETF is a transparent hierarchy, where participants take on explicit roles (e.g., Area Directors, Working Group Chairs), and because its processes are open we have visibility into the communication of people at different hierarchy levels over a long time period. Exploiting this, we utilise a temporal network dataset of 989,911 email interactions among 23,741 participants to study how hierarchy impacts communication patterns. We show that the middle levels of the IETF are growing in terms of their dominance in communications. Higher levels consistently experience a higher proportion of incoming communication than lower levels, with higher levels initiating more communications too. We find that, overall, communication tends to flow "up" the hierarchy more than "down". Finally, we find that communication with higher-levels is associated with future communication more than for lower-levels, which we interpret as "facilitation". We conclude by discussing the implications this has on patterns within the wider IETF and the impact our analysis can have for other organisations.

The public suffix list is a community-maintained list of rules that can be applied to domain names to determine how they should be grouped into logical organizations or companies. We present the first large-scale measurement study of how the public suffix list is used by open-source software on the Web and the privacy harm resulting from projects using outdated versions of the list. We measure how often developers include out-of-date versions of the public suffix list in their projects, how old included lists are, and estimate the real-world privacy harm with a model based on a large-scale crawl of the Web. We find that incorrect use of the public suffix list is common in open-source software, and that at least 43 open-source projects use hard-coded, outdated versions of the public suffix list. These include popular, security-focused projects, such as password managers and digital forensics tools. We also estimate that, because of these out-of-date lists, these projects make incorrect privacy decisions for 1313 effective top-level domains (eTLDs), affecting 50,750 domains, by extrapolating from data gathered by the HTTP Archive project.

Protocol standards, defined by the Internet Engineering Task Force (IETF), are crucial to the successful operation of the Internet. This paper presents a large-scale empirical study of IETF activities, with a focus on understanding collaborative activities, and how these underpin the publication of standards documents (RFCs). Using a unique dataset of 2.4 million emails, 8,711 RFCs and 4,512 authors, we examine the shifts and trends within the standards development process, showing how protocol complexity and time to produce standards has increased. With these observations in mind, we develop statistical models to understand the factors that lead to successful uptake and deployment of protocols, deriving insights to improve the standardisation process.

Use of formal protocol description techniques and code generation can reduce bugs in network packet parsing code. However, such techniques are themselves complex, and don't see wide adoption in the protocol standards development community, where the focus is on consensus building and human-readable specifications. We explore the utility and effectiveness of new techniques for describing protocol data, specifically designed to integrate with the standards development process, and discuss how they can be used to generate code that is safer and more trustworthy, while maintaining correctness and performance.

The past few years have seen significant developments in Single Board Computer (SBC) hardware capabilities. These advances in SBCs translate directly into improvements in SBC clusters. In 2018 an individual SBC has more than four times the performance of a 64-node SBC cluster from 2013. This increase in performance has been accompanied by increases in energy efficiency (GFLOPS/W) and value for money (GFLOPS/$). We present systematic analysis of these metrics for three different SBC clusters composed of Raspberry Pi 3 Model B, Raspberry Pi 3 Model B+ and Odroid C2 nodes respectively. A 16-node SBC cluster can achieve up to 60 GFLOPS, running at 80 W. We believe that these improvements open new computational opportunities, whether this derives from a decrease in the physical volume required to provide a fixed amount of computation power for a portable cluster; or the amount of compute power that can be installed given a fixed budget in expendable compute scenarios. We also present a new SBC cluster construction form factor named Pi Stack; this has been designed to support edge compute applications rather than the educational use-cases favoured by previous methods. The improvements in SBC cluster performance and construction techniques mean that these SBC clusters are realising their potential as valuable developmental edge compute devices rather than just educational curiosities.

Adaptive streaming over HTTP has become the de-facto standard for video streaming over the Internet, partly due to its ease of deployment in a heavily ossified Internet. Though performant in most on-demand scenarios, it is bound by the semantics of TCP, with reliability prioritised over timeliness, even for live video where the reverse may be desired. In this paper, we present an implementation of MPEG-DASH over TCP Hollywood, a widely deployable TCP variant for latency sensitive applications. Out-of-order delivery in TCP Hollywood allows the client to measure, adapt and request the next video chunk even when the current one is only partially downloaded. Furthermore, the ability to skip frames, enabled by multi-streaming and out-of-order delivery, adds resilience against stalling for any delayed messages. We observed that in high latency and high loss networks, TCP Hollywood significantly lowers the possibility of stall events and also supports better quality downloads in comparison to standard TCP, with minimal changes to current adaptation algorithms.

We consider the problem of securely distributing software updates to large scale clusters of heterogeneous edge compute nodes. Such nodes are needed to support the Internet of Things and low-latency edge compute scenarios, but are difficult to manage and update because they exist at the edge of the network behind NATs and firewalls that limit connectivity, or because they are mobile and have intermittent network access. We present a prototype secure update architecture for these devices that uses the combination of peer-to-peer protocols and automated NAT traversal techniques. This demonstrates that edge devices can be managed in an environment subject to partial or intermittent network connectivity, where there is not necessarily direct access from a management node to the devices being updated.

Until recently, cluster computing was too expensive and too complex for commodity users. However the phenomenal popularity of single board computers like the Raspberry Pi has caused the emergence of the single board computer cluster. This demonstration will present a cheap, practical and portable Raspberry Pi cluster called Pi Stack. We will show pragmatic custom solutions to hardware issues, such as power distribution, and software issues, such as remote updating. We also sketch potential use cases for Pi Stack and other commodity single board computer cluster architectures.

Current commodity Single Board Computers (SBCs) are sufficiently powerful to run mainstream operating systems and workloads. Many of these boards may be linked together, to create small, low-cost clusters that replicate some features of large data center clusters. The Raspberry Pi Foundation produces a series of SBCs with a price/performance ratio that makes SBC clusters viable, perhaps even expendable. These clusters are an enabler for Edge/Fog Compute, where processing is pushed out towards data sources, reducing bandwidth requirements and decentralizing the architecture. In this paper we investigate use cases driving the growth of SBC clusters, we examine the trends in future hardware developments, and discuss the potential of SBC clusters as a disruptive technology. Compared to traditional clusters, SBC clusters have a reduced footprint, are low-cost, and have low power requirements. This enables different models of deployment—particularly outside traditional data center environments. We discuss the applicability of existing software and management infrastructure to support exotic deployment scenarios and anticipate the next generation of SBC. We conclude that the SBC cluster is a new and distinct computational deployment paradigm, which is applicable to a wider range of scenarios than current clusters. It facilitates Internet of Things and Smart City systems and is potentially a game changer in pushing application logic out towards the network edge.

TCP suffers from incast collapse in data center networks when used with partition aggregate workloads due to inadequate congestion control parameters. This causes poor application performance by under-utilizing the network, and can be one of the limiting factors in low-latency, high-throughput environments. To resolve this, we present Omniscient TCP (OTCP), a Software Defined Networking (SDN) approach to compute environment-specific congestion control parameters based on centrally available network properties. Through experimental evaluation in Mininet, we show up to 12x and 31x reduction in Flow Completion Time (FCT) at the mean and 95th percentile, an 8x FCT improvement on highly congested networks when combined with DCTCP [1], as well as improved fairness and reduced end-to-end latency.

Real-time multimedia applications use either TCP or UDP at the transport layer, yet neither of these protocols offer all of the features required. Deploying a new protocol that does offer these features is made difficult by ossification: firewalls, and other middleboxes, in the network expect TCP or UDP, and block other types of traffic. We present TCP Hollywood, a protocol that is wire-compatible with TCP, while offering an unordered, partially reliable message-oriented transport service that is well suited to multimedia applications. Analytical results show that TCP Hollywood extends the feasibility of using TCP for real-time multimedia applications, by reducing latency and increasing utility. Preliminary evaluations also show that TCP Hollywood is deployable on the public Internet, with safe failure modes. Measurements across all major UK fixed-line and cellular networks validate the possibility of deployment.

We present initial measurements to determine if ECN is usable with UDP traffic in the public Internet. This is interesting because ECN is part of current IETF proposals for congestion control of UDP-based interactive multimedia, and due to the increasing use of UDP as a substrate on which new transport protocols can be deployed. Using measurements from the author's homes, their workplace, and cloud servers in each of the nine EC2 regions worldwide, we test reachability of 2500 servers from the public NTP server pool, using ECT(0) and not-ECT marked UDP packets. We show that an average of 98.97% of the NTP servers that are reachable using not-ECT marked packets are also reachable using ECT(0) marked UDP packets, and that ~98% of network hops pass ECT(0) marked packets without clearing the ECT bits. We compare reachability of the same hosts using ECN with TCP, finding that 82.0% of those reachable with TCP can successfully negotiate and use ECN. Our findings suggest that ECN is broadly usable with UDP traffic, and that support for use of ECN with TCP has increased.

With multimedia and Internet enabled devices being ubiquitous, mechanisms that ensure multimedia flows do not congest the Internet are crucial components of multimedia systems that are embraced rather than opposed by network service providers. The Real-time Transport Protocol (RTP) Circuit Breaker is designed to terminate RTP/UDP flows that cause excessive congestion in the network. Multimedia users congesting the network have their flows terminated, as dictated by the RTP circuit breaker congestion rule. Users who obtain little quality from a multimedia session, and consume network resources to no avail, should also cease transmission. This is the mandate of the RTP circuit breaker media usability rule. We propose an algorithm for this rule, and show that it avoids wasting network resources on flows that deliver no quality to the user.

The Real-time Transport Protocol (RTP) supports a range of video conferencing, telephony, and streaming video applications, but offers few native security features. We discuss the problem of securing RTP, considering the range of applications. We outline why this makes RTP a difficult protocol to secure, and describe the approach we have recently proposed in the IETF to provide security for RTP applications. This approach treats RTP as a framework with a set of extensible security building blocks, and prescribes mandatory-to-implement security at the level of different application classes, rather than at the level of the media transport protocol.

The packet loss characteristics of Internet paths that include residential broadband links are not well understood, and there are no good models for their behaviour. This complicates the design of real-time video applications targeting home users, since it is difficult to choose appropriate error correction and concealment algorithms without a good model for the types of loss observed. Using measurements of residential broadband networks in the UK and Finland, we show that existing models for packet loss, such as the Gilbert model and simple hidden Markov models, do not effectively model the loss patterns seen in this environment. We present a new two-level Markov model for packet loss that can more accurately describe the characteristics of these links, and quantify the effectiveness of this model. We demonstrate that our new packet loss model allows for improved application design, by using it to model the performance of forward error correction on such links.

Data Center (DC) networks exhibit much more centralized characteristics than the legacy Internet, yet they are operated by similar distributed routing and control algorithms that fail to exploit topological redundancy to deliver better and more sustainable performance. Multipath protocols, for example, use node-local and heuristic information to only exploit path diversity between shortest paths. In this paper, we use a measurement-based approach to schedule flows over both shortest and non-shortest paths based on temporal network-wide utilization. We present the Baatdaat flow scheduling algorithm which uses spare DC network capacity to mitigate the performance degradation of heavily utilized links. Results show that Baatdaat achieves close to optimal Traffic Engineering by reducing network-wide maximum link utilization by up to 18% over Equal-Cost Multi-Path (ECMP) routing, while at the same time improving flow completion time by 41% - 95%.

Thorup-Zwick (TZ) compact routing guarantees sublinear state growth with the size of the network by routing via landmarks and incurring some path stretch. It uses a pseudo-random landmark selection designed for static graphs, and unsuitable for Internet routing. We propose a landmark selection algorithm for the Internet AS graph that uses k-shells decomposition to choose landmarks. Using snapshots of the AS graph from 1997-2010, we demonstrate that the ASes in the kmax-shell are highly-stable over time, and form a sufficient landmark set for TZ routing in the overwhelming majority of cases (in the remainder, adding the next k-shell suffices). We evaluate path stretch and forwarding table sizes, and show that these landmark sets retain low average path stretch with tiny forwarding tables, but are better suited to the dynamic nature of the AS graph than the original TZ landmark selection algorithm.

Packet loss is a major problem for real-time Internet applications. Markov models of packet loss are often used to develop and evaluate the performance of these applications. Despite their wide use, these models have not been validated in terms of how well they capture the loss conditions experienced by residential Internet users. We evaluate the accuracy of common packet loss models using traces of IPTV-like traffic measured on residential ADSL and Cable links, and find that these models are insufficient to capture the observed packet loss patterns. We introduce a new type of model, incorporating packet delay information, and show improved accuracy over previous models.

Measurement and inference in data centers present a set of opportunities and challenges distinct from the Internet domain. Existing toolsets may be perturbed or be mislead by issues related to virtualization. Yet, while equally confronted by scale, data centers are relatively homogenous and symmetric. We believe these may be attributes to be exploited. However, data is required to better evaluate our hypotheses. Therefore, we introduce our efforts to gather data using a single framework from which we can launch tests of our choosing. Our observations reinforce recent claims, but indicate changes in the network. They also reveal additional obfuscations stemming from virtualization.

Spotify is a popular music-streaming service which has seen widespread use across Europe. While Spotify's server- side behaviour has previously been studied, little is known about the client-side behaviour. In this paper, we describe an experimental study where we collect packet headers for Spotify traffic over multiple 24-hour time frames at a client host. Two distinct types of behaviour are observed, when tracks are being downloaded, and when the client is only serving requests from other peers. We also note wide variation in connection lifetimes, as seen in other studies of peer-to-peer systems. These findings are relevant for improving Spotify itself, and for the designers of other hybrid peer-to-peer and server-based distribution architectures.

Little performance data currently exists for streaming high-quality Internet video to residential users. Data on streaming performance will provide valuable input to the design of new protocols and applications, such as congestion control and error-correction schemes, and sizing playout buffers in video receivers. This paper presents measurements of streaming real-time UDP traffic to a number of residential users, and discusses the basic characteristics of the data.

Quality of experience (QoE) is an important, and admittedly overloaded, concept for the emerging IPTV services. Service providers are continuously working towards delivering a better TV experience. To this effect, cost-effective and scalable tools are highly desirable for QoE monitoring, diagnostics and reporting. In this paper, we demonstrate that the RTP control protocol and its network tomography extensions can satisfy the needs of the providers in collecting and reporting both detailed and summarized information using several numerical examples based on real-life scenarios.

Packet loss is one of the principal threats to quality of experience for IPTV systems. However, the packet loss characteristics of the residential access networks which carry IPTV are not widely understood. We present packet level measurements of streaming IPTV-like traffic over four residential access links, and describe the extent and nature of packet loss we encountered. We discuss the likely impact of these losses for IPTV traffic, and outline steps which can ameliorate this.

Conventional on-demand route discovery for ad hoc routing protocols extensively use simple flooding, which could potentially lead to high channel contention, causing redundant retransmissions and thus excessive packet collisions in the network. This phenomenon has been shown to greatly increase the network communication overhead and end to end delay. This paper proposes a new probabilistic counter-based method that can significantly reduce the number of RREQ packets transmitted during route discovery operation. Our simulation results reveal that equipping AODV routing protocol with the proposed probabilistic counter-based route discovery method can result in significant performance improvements in terms of routing overhead, MAC collisions and end-to-end delay while still achieving a good throughput.

We review the design and implementation of UltraGrid, a new high definition video conferencing system, and present some experimental results. UltraGrid was the first system to support gigabit rate high definition interactive video conferencing on commodity systems and networks, and we present measurements to illustrate behavior of production networks subject to such real time traffic. We illustrate the benefits of hybrid IP/provisioned optical networks over best effort IP networks for this class of traffic, and motivate the development of congestion control algorithms for interactive conferencing on best effort IP networks

We describe how the new datagram congestion control protocol (DCCP) can be used as a bearer for the real-time transport protocol (RTP) to provide a congestion controlled basis for networked multimedia applications. This is a step towards deployment of congestion control for such applications, necessary to ensure the future stability of the best-effort network if high-bandwidth streaming and IPTV services are to be deployed outside of closed QoS-managed networks

We discuss the evolution of teleconferencing and networked visualization applications to support 3-dimensional display technologies. The implications of a continuation of Moore's law, coupled with constraints on device clock rate due to power consumption, suggest that future end system and network architectures will become increasingly parallel in nature. Given this, we review trends in programming language design that will ease development of highly concurrent systems, and suggest how network transport protocols might evolve to support them.

We performed end-to-end measurements of UDP/IP flows across an Internet backbone network. Using this data, we characterized the packet reordering processes seen in the network. Our results demonstrate the high prevalence of packet reordering relative to packet loss, and show a strong correlation between packet rate and reordering on the network we studied. We conclude that, given the increased parallelism in modern networks and the demands of high performance applications, new application and protocol designs should treat packet reordering on an equal footing to packet loss, and must be robust and resilient to both in order to achieve high performance

It is well known that congestion control is a key issue for the safe deployment of multimedia applications over IP. We describe our initial experiences implementing TCP-friendly congestion control in a system designed to deliver HDTV content over IP networks. In particular we discuss the effects of packet reordering on the calculated throughput, and highlight the problems this can pose for high-rate applications.

We describe an approach to scaling video conferencing, with the use of active agents. Such agents tileNvideo frames into one, by modification of their respective meta-data and adjustment of their video frame rate if necessary. The spatial tiling agents are located within a network, and participants in the session unicast video to the “closest” agent. The agent then multicast the tiled video to the group of all participants. Results show that spatial tiling increases the ability of the end-user to receive large numbers of video streams and reduces network load both in terms of bandwidth and in packets per second. The result is a significant scaling boost to video conferencing systems.

We discuss the use of interleaving as a bandwidth efficient means of protecting audio streams from the effects of packet loss on the Internet. The adverse effects of interleaving on IP/UDP/RTP header compression are noted and a number of schemes which remedy this problem are discussed.