Anomaly detection (AD) plays a critical role in a wide variety of big data applications, including cybersecurity, monitoring, and network systems. It consists in finding patterns in time series data that indicate unexpected events such as faults or defects. Traditional AD approaches, predominantly based on reconstruction techniques, often yield suboptimal performance, particularly when anomalies are present in the training set. Conversely, contrastive learning (CL) has shown significant performance in image processing tasks and is increasingly applied in time series data classification and forecasting. However, traditional CL frameworks are not well-adapted for time series AD due to two key challenges. First, AD is typically performed only on normal instances, and thus CL does not benefit from knowledge about anomalous instances. Second, the temporal nature of time series data is often neglected when computing time series similarity, thereby hindering the effective learning of time series representation.To overcome these limitations, we propose CATS, a novel approach that leverages a temporal similarity measure to learn time series representations. Moreover, through negative data augmentation, CATS generates a more realistic distribution of anomalies, which enables anomaly-informed CL. Extensive experiments conducted on six real-world datasets demonstrate that CATS outperforms existing AD methods. Our results highlight the efficacy of CATS in enhancing time series AD performance in big data environment across various application domains.

Deep learning (DL) has been successfully applied to encrypted network traffic classification in experimental settings. However, in production use, it has been shown that a DL classifier’s performance inevitably decays over time. Re-training the model on newer datasets has been shown to only partially improve its performance. Manually re-tuning the model architecture to meet the performance expectations on newer datasets is time-consuming and requires domain expertise. We propose AutoML4ETC, a novel tool to automatically design efficient and high-performing neural architectures for encrypted traffic classification. We define a novel, powerful search space tailored specifically for the early classification of encrypted traffic using packet header bytes. We show that with different search strategies over our search space, AutoML4ETC generates neural architectures that outperform the state-of-the-art encrypted traffic classifiers on several datasets, including public benchmark datasets and real-world TLS and QUIC traffic collected from the Orange mobile network. In addition to being more accurate, AutoML4ETC’s architectures are significantly more efficient and lighter in terms of the number of parameters. Finally, we make AutoML4ETC publicly available for future research.

Over the past twenty years, a plethora of methods have been proposed for encrypted traffic classification (ETC), while the Server name indication (SNI) is deemed to solve the problem of classification for TLS traffic. However, SNI-based classification has its pitfalls and the SNI will likely be pushed into the encrypted tunnel in the future. In this work, we envision a futuristic scenario in which encrypted SNI is the norm and labeled traffic flows are scarce. In such settings, we tackle the problem of traffic classification at ISP level using few-shot learning. By means of six real-world ISP-level datasets collected between 2019 and 2021 and two publicly available client-side datasets, we study the performance of a few-shot learner on TLS data, including its cross-dataset generalizability. We further investigate the effect of the number of required labeled samples on the learner's performance. Our experiments show that the dataset-specificity of deep learners carries over to few-shot meta-learning, and calls for addressing the problem of generalizability for deep learning architectures.

Low-Iatency (LL) applications, such as the increasingly popular cloud gaming (CG) services, have stringent latency requirements. Recent network technologies such as L4S (Low Latency Low Loss Scalable throughput) propose to optimize the transport of LL traffic and require efficient ways to identify it. A previous work proposed a supervised machine learning model to identify CG traffic but it suffers from limited processing rate due to a pure software approach and a lack of generalization. In this paper, we propose a hybrid P4/NFV architecture, where a hardware Tofino based P4 implementation of the feature extraction functionality is deployed in the data plane and a unsupervised model is used to improve classification results. Our solution has a better processing rate while maintaining an excellent identification accuracy thanks to model adaptations to cope with P4 limitations and can be deployed at ISP level to reliably identify the CG traffic at line rate.

Cloud Gaming (CG) has been gaining a lot of interest and major actors have entered this market such as Google, Nvidia, Sony or Microsoft. They operate CG platforms that attract an increasing number of players worldwide. This type of traffic is highly demanding for network infrastructures because it requests simultaneously high bandwidth, low delay and no traffic degradation (interruptions or jitter) to ensure a good end-user’s QoE. To improve the delivery of low-latency applications, new Active Queue Management architectures like L4S (Low Latency, Low Loss, Scalable Throughput) are proposed. Currently, traffic is routed to a low-latency queue only based on the presence of the Explicit Congestion Notification bit (ECN) in the IP header, but this is too restrictive and can be easily manipulated. Instead, we aim at analyzing and detecting CG traffic based on its inherent characteristics, to forward the packets in the low-latency queue. This paper presents our models to efficiently detect CG traffic based on flow-level features among other highbitrate applications transported over UDP. The evaluation proves that our model based on decision trees achieves very good results (98.5% accuracy) and can be realistically deployed as a Virtualized Network Function at the edge, handling more than 10Gb/s of medium-sized flows on a low-end server. Our network captures and source code are open to ensure reproducible results.

The Low-Latency Low-Loss Scalable throughput (L4S) architecture has recently been proposed to reduce the network latency of low-latency services and to allow their flows to coexist with classic ones in the same domain. This coexistence implies monitoring and security challenges. However current monitoring methods, primarily based-on sampling and polling, exhibit performance and granularity limitations. This paper describes the challenges for monitoring LL services and details our solution when introducing a fine-grained and real-time monitoring capability in our P4-based L4S implementation using In-band Network Telemetry. The initial experimental evaluation shows that our solution is able to monitor the metrics of an L4S switch with very few networking and processing overhead and without disturbing the L4S behaviour.

Detecting abnormal network events is an important activity of Internet Service Providers particularly when running critical applications (e.g., ultra low-latency applications in mobile wireless networks). Abnormal events can stress the infrastructure and lead to severe degradation of user experience. Machine Learning (ML) models have demonstrated their relevance in many tasks including Anomaly Detection (AD). While promising remarkable performance compared to manual or threshold-based detection, applying ML-based AD methods is challenging for operators due to the proliferation of ML models and the lack of well-established methodology and metrics to evaluate them and select the most appropriate one. This paper presents a comprehensive evaluation of eight unsupervised ML models selected from different classes of ML algorithms and applied to AD in the context of cloud gaming applications. We collect cloud gaming Key Performance Indicators (KPIs) time-series datasets in real-world network conditions, and we evaluate and compare the selected ML models using the same methodology, and assess their robustness to data contamination, their efficiency and computational complexity. In addition to the traditional F1-score performance metric used in anomaly detection, we use Matthews Coefficient Correlation (MCC) to better differentiate between models’ efficiencies. Our proposed methodology relies on window-based anomaly detection techniques as they are more useful for network operators compared to single point detection approaches. However, we found most existing window-based approaches to lack in accuracy and may under or over-estimate a model’s performance. Therefore, in this paper, we propose a novel Window Anomaly Decision (WAD) approach that overcomes these drawbacks. We leverage our experimental results to provide insights about the most relevant models for detecting QoE degradation and offer recommendations on their suitability for different application requirements.

Cloud gaming applications have gained great adoption on the Internet particularly benefiting from the wide availability of broadband access networks. However, they still fail to meet users’ quality requirements when accessed using cellular networks due to common wireless channel degradations. Machine Learning (ML) techniques can be leveraged to detect such anomalies during users’ cloud gaming sessions. In this respect, unsupervised ML approaches are particularly interesting since they do not require labeled datasets. In this work, we investigate these approaches to understand their performance and their robustness. Our dataset consists of game sessions played on the public Google Stadia Cloud Gaming servers. The game sessions are played using a 4G network emulation replicating the capacity variations sampled on a commercial 4G network. We compare different models ranging from traditional approaches to deep learning and we evaluate their default performance while varying the level of contamination in their training datasets. Our experiments show that Auto-Encoders models achieve the best performance without contamination while the OC-SVM and the Isolation Forest are the most robust to data contamination.

With the recent technological evolutions in networks and increased deployment of multi-tier clouds, cloud gaming (CG) is gaining renewed interest and is expected to become a major Internet service in the upcoming years. Many companies have launched powerful platforms such as Google Stadia, Nvidia GeForce Now, Microsoft xCloud, Sony PlayStation Now among others, to attract players. However, for all end-users to fully enjoy their gaming sessions over the wide range of network access qualities, CG platforms must adapt their traffic. In this paper, we present the outcome of real-life measurements performed between April and July 2021 on the four aforementioned CG platforms, configuring different network constraints like packet loss, throughput decrease, latency increase and jitter variation to observe the behavior of these CG platforms under extreme network conditions. Our findings show that the four platforms exhibit different adaptation behaviors. Moreover, many cases result in a degraded QoS, leaving room for further improvements at both application and/or network levels.

New types of services with low-latency requirements have become a major challenge for the future Internet. Many optimizations, all targeting the latency reduction have been proposed. Among them, jointly re-architecting congestion control and active queue management has been particularly considered. In this effort, the L4S (Low Latency, Low Loss and Scalable Throughput) proposal aims at allowing both classic and low-latency traffic to cohabit within a single node architecture. Although this architecture sounds promising for latency improvement, it can be exploited by an attacker to perform malicious actions whose purposes are to defeat its low-latency feature and consequently make their supported applications unusable. In this paper, we analyze a set of weaknesses of L4S architecture and show that application-layer protocols such as QUIC can easily be hacked in order to exploit the over-sensitivity of those new services to network variations. By implementing undesirable flows in a real testbed and evaluating how they impact the proper delivery of low-latency flows, we demonstrate their reality and relevance for future deployments.

Low-Iatency applications, such as cloud gaming or cloud robotics are very demanding in terms of network latency. The IETF defines the L4S (Low Latency Low Loss Scalable throughput) architecture, to enable the delivery of high-bitrate low-latency applications without degrading the quality of other services. To deploy and upgrade L4S in network equipment to follow the transport protocols entering an age of quick evolutions, P4 (Programming Protocol-Independent Packet Processor), a programmable data plane concept, can help since it facilitates the deployment of networking software. In this paper, we propose a P4-based L4S solution and the performed evaluation proves our system behaves as expected. Furthermore, to be largely deployed, L4S should also be efficient under real cellular network conditions, which can vary over time and where the main network bottlenecks are. However, our evaluation shows limitations of L4S in providing high throughput while ensuring low latency delivery with time varying network conditions.

Being on endpoints, Content Providers can easily evaluate end users' Web browsing quality of experience (Web QoE) by accessing in-browser computed application-level metrics. Because of end-to-end traffic encryption, it is becoming considerably harder for Internet Service Providers (ISPs) to evaluate the Web QoE of their customers, which is important for management purposes. In this paper, we propose data-driven machine learning techniques and exact flow-level algorithmic methods to infer well-known application-level Web performance metrics (such as SpeedIndex and Page Load Time) from raw encrypted streams of network traffic. We prove the efficiency of our approach taking as input a unique dataset of more than 200,000 experiments, targeting a large set of popular pages (Alexa top-500), from probes from several ISPs networks, with different browsers (Chrome, Firefox) and viewport combinations. Results show that our data-driven models are not only accurate for several Web performance metrics, but also feature the ability to generalize to previously unseen conditions. Furthermore, we discuss how our extremely lightweight flow-level method has a provable accuracy on a specific metric, and is thus of particular appeal from a deployment viewpoint.

Quality of Experience (QoE) inference, and particularly the detection of its degradation is an important management tool for ISPs. Yet, this task is made difficult due to widespread use of encryption on the data-plane on the one hand so that measuring QoE is hard, and to the ephemeral properties of the web content on the other hand so that changes in QoE indicators may be rooted in changes in properties of the content itself, more than being caused by network-related events. In this paper, we phrase the QoE degradation detection issue as a change point detection problem, that we tackle by leveraging a unique dataset consisting on several hundreds thousands browsing sessions spanning multiple months. Our results, beyond showing feasibility, warn about the exclusive use of QoE indicators that are very close to content, as changes in the content space can lead to false alarms that are not tied to network-related problems.

Web browsing is the most important Internet service, and offering the best performance to end-users is of prime importance. The World Wide Web Consortium (W3C) has brought along the Page Load Time (PLT) metric as a QoE (Quality of Experience) and QoS (Quality of Service) benchmarking indicator, which is nowadays the de facto web metric used by researchers, large service companies and web developers. Although alternative web metrics have been introduced to measure part of the loading process, the techniques used need additional computing power and timings are not offered in real-time. In order to provide real-time fined-grained timings during web browsing measurement campaigns, we present in this paper the TFVR (Time for Full Visual Rendering), a technique being browser-based to calculate the Above-The-Fold (ATF) offering the loading time of the visible portion at first glance of a web page. The TFVR exposes fine-grained timings such as networking and processing time for every downloaded resource. Based on a measurement campaign on top 10,000 Alexa websites, we have been able to better quantify and identify web page loading inefficiencies through a tool we have designed, namely, MORIS (Measuring and Observing Representative Information on webSites).

For a few years, Network-Function Virtualization (NFV) acts as the most promising solution for the flexible implementation and management of future network services. If most of current efforts in this area focus on IP-based Virtual Network Functions (VNF), the case of Information-Centric Networking (ICN) is interesting since it can demonstrate that NFV is a promising technology for ISP to deploy such new innovative network stacks. In this context, we propose to design and implement a NFV compliant architecture to easily deploy ICN islands. Especially, at the core of this architecture, we present an HTTP/NDN gateway, which enables our network to carry real HTTP traffic. Finally, we show early functional experimental results of an initial testbed deployment exhibiting the capability of our global infrastructure to retrieve the top- 1000 of the most popular web sites.

Many applications nowadays use HTTP. HTTP/2, standardised in February 2015, is an improvment of HTTP/1.1. However it is still running on top of TCP/TLS and can thus suffer from performance issues, such as the number of RTTs for the handshake phase and the Head of Line blocking. Google proposed the QUIC (Quick UDP Internet Connection) protocol, an user level protocol, running on top of UDP, to solve those issues. Google argues that the response time (Page Load Time) is shorter and thus the end-user experience better. First papers evaluated the intrinsic performances of QUIC, but none compared QUIC with the network, the website structure and the involved actors in mind. In this paper, we present the results of our evaluation, performed on a local testbed as well as on Internet, and our analysis to identify in which conditions QUIC is of interest, which actors can benefit from having QUIC deployed in the network and what impacts QUIC can lead to.

Web browsing protocols are currently gaining the interest of the researchers. Indeed, HTTP/2, an improvement of HTTP/1.1 has been standardized in 2015 and meanwhile, Google proposed another transport protocol, QUIC (Quick UDP Internet Connection). The main objective of the two protocols is to improve end-users quality of experience and communications security. Current HTTP/2-based web servers rely on the standardized TLS (Transport Layer Security) protocol, on top of TCP. Google has developed its own security system, natively integrated within QUIC, and runs on top of UDP. If performance issues, comparing HTTP/2 over TLS/TCP and QUIC/UDP, have been investigated by few researchers, no one studied the security aspects of the two transport protocols. This paper aims at filling this gap and proposes a first security analysis of TLS/TCP and QUIC/UDP. Based on their characteristics, this paper identifies the vulnerabilities of the two protocols and evaluates their impacts on HTTP/2-based web services. This study can enable web servers developers or administrators to either select TLS/TCP or QUIC/UDP.

As the number of devices which could be potentially connected to the Internet scales up, as the amount of traffic generated by these devices will explode, it is necessary to reconsider the underlying protocols which will support the Internet of Things. The request/response semantics of CCN are well suited to the retrieving data from a set of sensors and we consider here the deployment of CCN to retrieve missing objects in a distributed environment. We developed a demonstrator of it as a proof-of-concept. We then consider the scalability of such system and demonstrate how the combination of a Bloom Filter mechanism in addition to the CCN primitives allow for a very scalable deployment of an object retrieval function.

One of the crucial building blocks for Information Centric Networking ICN is a name based routing scheme that can route directly on content names instead of IP addresses. However, moving the address space from IP addresses to content names brings the scalability issues to a whole new level, due to two reasons. First, name aggregation is not as trivial a task as the IP address aggregation in BGP routing. Second, the number of addressable contents in the Internet is several orders of magnitude higher than the number of IP addresses. With the current size of the Internet, name based, anycast routing is very challenging specially when routing efficiency is of prime importance. We propose a name-based routing scheme αRoute for ICN that offers efficient bandwidth usage, guaranteed content lookup and scalable routing table size. αRoute consists of two components: an alphanumeric Distributed Hash Table DHT and an overlay to underlay Internet topology mapping algorithm. Simulation results show that αRoute performs significantly better than Content Centric Network CCN in terms of network bandwidth usage, lookup latency and load balancing.

Network operators are currently very cautious before deploying a new network equipment. This is done only if the new networking solution is fully monitored, secured and can provide rapid revenues (short Return of Investment). For example, the NDN (Named Data Networking) solution is admitted as promising but still uncertain, thus making network operators reluctant to deploy it. Having a flexible environment would allow network operators to initiate the deployment of new network solutions at low cost and low risk. The virtualization techniques, appeared a few years ago, can help to provide such a flexible networking architecture. However, with it, emerge monitoring and security issues which should be solved. In this paper, we present our secure virtualized networking environment to deploy new functions and protocol stacks in the network, with a specific focus on the NDN use-case as one of the potential Future Internet technology. As strong requirements for a network operator, we then focus on monitoring and security components, highlighting where and how they can be deployed and used. Finally, we introduce our preliminary evaluation, with a focus on security, before presenting the test bed, involving end-users consuming real contents, that we will set up for the assessment of our approach.

Centralized social networking and media sharing portals provide inadequate support for preserving user privacy, content ownership and control. These problems can be mitigated through distributed Web services as demonstrated by a number of academic projects and industrial deployments. In general, these distributed services do not assign globally recognized, persistent names to the user devices. As a result, these solutions work in isolation and also cannot inter-operate with traditional Web technology. In this work, we present a decentralized and scalable platform, named pWeb, for distributing web services, like online social networks and media streaming, across end-user devices. pWeb assigns Internet compatible names to end-user devices, and provides name resolution and directory services. A user can retain ownership, and make the services and contents in his devices searchable and accessible at different privacy levels, e.g., friends, family and public. New services can be easily developed and deployed over the pWeb platform. We have developed a working prototype of the platform, and to demonstrate its effectiveness we have implemented a video streaming application for Android and Windows platforms. We also present performance results from our prototype implementation.

Distributed services provided by Content Delivery Networks (CDNs) and Clouds are of increasing popularity. They are designed to offer powerful solutions for developing new services meeting users expectations while improving the Quality-of-Experience (QoE). It results of a growing traffic demand on network resources. In such a context, traffic optimization becomes a key challenge for both networks operators and CDN/Cloud services providers. This paper presents a cross-layer framework promoting the collaboration between the network and the service layers through a mutual exchange of information for an effective traffic optimization. CDN/Cloud service providers can expose high-level information about their needs and constraints, which helps network operators to guide them in their application-level traffic management, to best use the network resources. Our evaluation comparing the performance of our cross-layer optimization framework with other approaches demonstrates that noticeable gains can be achieved on the network utilization and the perceived quality of services.

One of the crucial building blocks for Information Centric Networking (ICN) is a name based routing scheme that can route directly on content names instead of IP addresses. However, moving the address space from IP addresses to content names brings scalability issues to a whole new level, due to two reasons. First, name aggregation is not as trivial a task as the IP address aggregation in BGP routing. Second, the number of addressable contents in the Internet is several orders of magnitude higher than the number of IP addresses. With the current size of the Internet, name based, anycast routing is very challenging specially when routing efficiency is of prime importance. We propose a novel name-based routing scheme (αRoute) for ICN that offers efficient bandwidth usage, guaranteed content lookup and scalable routing table size.

The peer—to—peer paradigm has great potential of providing the next generation Web hosting infrastructure. Profound advancements in P2P technology in the last decade have proven its capability to provide functionality similar to traditional client—server systems at a much larger scale with relatively lower cost. Existing centralized website hosting technology has a number of inherent deficiencies including scalability, single point of failure, administration overhead, hosting expenses, etc. P2P Web hosting can effectively address these problems and hence open a new era for next generation Web hosting. However peer availability and content location are highly dynamic in a P2P network. This dynamism raises a number of research challenges related to naming, addressing, indexing, and searching in a P2P environment. In this paper we identify the practical requirements for devising a secure, persistent, and human—friendly naming scheme for P2P Web hosting and propose a novel naming scheme that satisfies all these requirements. We also present extensive simulation results validating the accuracy, scalability and fault-resilience of the proposed naming scheme.

Ensuring content availability in a persistent manner is essential for providing any consistent service over peer-to-peer (P2P) systems. This paper introduces an efficient protocol, called DATA, to design highly available P2P systems irrespective of peer uptime and churn. Our approach utilizes the diurnal pattern of globally dispersed peers to develop a grouping strategy where each group aims to ensure 24 × 7 data availability within the group. Simulation results reveal that our protocol converges fast and ensures high availability for each group with minimal overhead.

Content-Centric Network is a novel Internet design that investigates the shifting of the Internet usage from browsing to content dissemination. This new Internet architecture proposal can bring many benefits and it has attracted many research works. When we study on these research, we found that one of the important components, the Pending Interest Table (PIT), did not get much attention. Since that in CCN the networking behaviours are no longer based on endpoints location but rather on every piece of the content itself, and the PIT is involved in both the forwarding processes upstream and downstream, in case of large amount of requests, the table size is a big issue, that leads to a large required memory space for implementing such a CCN node. In this paper, we propose a distributed PIT table, named DiPIT, where a part of the PIT is on every interface. Our approach relies on Bloom Filters in order to reduce the necessary memory space for implementing the PIT, completed with a central Bloom Filter for limiting the false positives, generated by the individual Bloom Filters. The evaluations we have performed highlight that our DiPIT approach can significantly reduce the memory space (up to 63%) in the CCN node and support a higher incoming packet throughput, compared to the hash table technology, which is largely implemented in current routers.

Video contents are now dominant in the Internet traffic and more and more people watch Live streamed contents. Started with a simple client/server architecture, Live streaming is now evolving towards a CDN-based network or a P2P-based distribution. The evolution is expected to provide a better quality to end-users while reducing costs for the content providers. In parallel with the evolution of the architectures, the access networks of the customers are also evolving, in terms of link capacities. More and more people can have a high broadband access connection. This is linked to evolution of xDSL networks but also to the deployment of FTTH (Fiber To The Home) networks. With the FTTH deployment, the issue of the best delivery model is raised up. Started from the current situation in the France Telecom network, we forecasted a deployment of FTTH customers (5 to 25% of ADSL customers migrating to FTTH) and evaluated the network load as well as the cost for a network operator to provide a live streaming service to its customers, on various architectures: Centralised server, regional servers (operator CDN-like network), and both assisted with a national P2P network and with a regional P2P network (e.g. ALTO-like systems where local peers are preferred to remote peers). The results of our techno-economic assessment highlight the benefit of a P2P-based delivery system in relation with the deployment of FTTH, more visible in case of network-aware (regional) P2P.

Peer-to-Peer (P2P) delivery systems, such as eDonkey, Bittorrent, attracted many people who want to share files. Other P2P systems, used for broadcasting video contents, also gained in popularity (e.g., Live systems such as PPLive, PPStream, UUSee, etc.). In the past few years, new streaming applications, initially designed for User Generated Contents (UGC) have come up and are now widely used to share video contents (e.g., Youtube, Hulu, etc.). Their growing success raises the question of the delivery architecture: will a client/server model still be of good quality? In this paper, we advocate the migration of such applications towards a P2P delivery architecture for scalability and quality purposes. A huge amount of the network traffic is currently related to P2P and UCG applications. However, most of the contents are illegal and therefore badly perceived by majors, governments and ISPs. Furthermore, because of the traffic load it generates in the network, ISPs do not really like it. In this paper, we propose a system that could be acceptable for ISPs since it aims at controlling that only legal contents are distributed and at reducing and optimizing the use of the network, via an active role played by ISPs in the peer selection process. Experiments we have performed in a real-life configuration environment proved the feasibility and efficiency of the proposed solution.

The Bittorrent P2P (Peer-to-Peer) network is now well-known and widely used. In Europe, it is mainly used with people connected to ADSL networks. However, with the emergence of various access networks with various capabilities (bandwidth, delay, etc.), we might wonder if Bittorrent is well suited to those heterogeneous networks. Moreover, some mobile 3G network operators even forbid the use of P2P networks in their contract (and eventually block it) because it overloads the shared wireless links. This heterogeneity of networks as well as the the possibility that ISPs block P2P traffic, could have an impact on the Bittorrent system. This is what this paper addresses with simulations of a swarm composed of peers, connected to heterogeneous access networks. The simulations we performed enable us to highlight that the Bittorrent protocol is not optimised for being used from various ISP access networks and thus we propose a simple adaptation of the Bittorrent algorithm, which classifies peers, depending on their access network capabilities and unchokes peers, based on their class and no more independently. This adapted algorithm allows to maintain a good QoE (Quality of Experience) to end-users while satisfying ISPs' constraints since it does no longer load the wireless access network.

The peer-to-peer paradigm has great potential of contributing to the next generation web-hosting infrastructure. Profound advancements in P2P technologies in the last decade have proven their capability to provide the same functionality as traditional client-server systems at a much larger scale and much lower cost. Existing centralized website hosting technology has a number of inherent deficiencies, including: scalability issues; single point of failure; administrative overhead; and hosting expenses. P2P Web hosting can effectively address these problems and open a new era for the next generation web technology. Unlike the current web however, peer availability and content placement are highly dynamic in P2P networks. This dynamism raises a number of research challenges related to naming, indexing, searching and hosting in P2P environments. In this paper we identify the practical requirements for devising a persistent naming scheme for P2P web-hosting on top of highly dynamic non-persistent P2P networks and present a novel naming architecture for satisfying these requirements.

WMN (wireless multi-hop mesh network) is currently a main topic and viewed as a promising and cost-effective solution to offer broadband Internet access: for instance, an area where deployment of wired infrastructure is not benefit (from economic perspective) or impossible such as rural zones. Furthermore, WMN enables to extend coverage thanks to the multi-hop capabilities of the routing protocol.The WMN is very interesting, and some network operators perform realworld experiments and plan a possible deployment of such networks in the near future. Also, MANET (Mobile Ad-hoc Network) is currently a promising solution because it can be deployed quickly as a temporary network, after a disaster for instance. However, multi-hop networking, used for both mesh networking and ad hoc networking presents specific characteristics compared to traditional wired or wireless infrastructure-based networks. Amongst others, the topology changes, the link instability, the interferences and influence of external parameters (human presence for instance) have a great impact on the network behavior and performance. Thus, deploying such a network without a monitoring tool is ineffective. This paper introduces a monitoring tool for multi-hop networks we have developed which allows network administrators as well as applications developers to have a better understanding of the networks status (global view of the network as well as information per node), the application behavior on the network and how the network state can impact their performance.

Ambient networks (ANs) are dynamically changing and heterogeneous as they consist of potentially large numbers of independent, heterogeneous mobile nodes, with spontaneous topologies that can logically interact with each other to share a common control space, known as the ambient control space. ANs are also flexible i.e. they can compose and decompose dynamically and automatically, for supporting the deployment of cross-domain (new) services. Thus, the AN architecture must be sophisticatedly designed to support such high level of dynamicity, heterogeneity and flexibility. We advocate the use of service specific overlay networks in ANs, that are created on-demand according to specific service requirements, to deliver, and to automatically adapt services to the dynamically changing user and network context. This paper presents a self-management approach to create, configure, adapt, contextualise, and finally teardown service specific overlay networks.

With the increasing heterogeneity of Internet enabled devices and Internet access technologies, media content may often need to be adapted to best meet the user or application needs. However, server-side adaptation has shown its limitations, leading to the development of network-side adaptation techniques. Overlay networks have emerged as a possible solution to enable data processing between users and the content server, as it allows to transparently include media processing nodes into the end-to-end media path. Nevertheless, to deal with multimedia streams in an efficient way, current proposals lack application awareness when k comes to routing decisions. Typically overlay networks only consider IP header information when routing packets. In this paper we introduce a new concept that shall enable media aware routing via the use of overlay networks. The proposed routing approach considers service and application information to improve routing decisions based on the user/application requirements. In our proposal, service-specific overlay networks (SSONs) are created for every service, which allows customisation of the network resources. SSONs include overlay nodes with adaptation capability. The data routing in the SSON is performed using the media aware overlay routing logic. This paper presents the concept, along with a proposed architecture designed to provide a media aware routing service. The advantage of the proposed functionality is illustrated based on a mobile user scenario.

UNLABELLED: ProViz is a tool for the visualization of protein-protein interaction networks, developed by the IntAct European project. It provides facilities for navigating in large graphs and exploring biologically relevant features, and adopts emerging standards such as GO and PSI-MI. AVAILABILITY: ProViz is available under the GPL and may be freely downloaded. Source code and binaries are available at http://cbi.labri.fr/eng/proviz.htm CONTACT: [email protected]