International audience

Dynamic networks like Online Social Networks or Disruption Tolerant Networks (DTNs), when considering their spatial, temporal and size complexity, even if partly wired, are exposed to nodes and links churns and failures which can be modeled with dynamic graphs with time varying edges and vertices. Recently, it has been shown that dynamic networks exhibit some regularity in their temporal contact patterns. The impact of this regularity on network performances has not been well studied and analyzed. One of the most interesting problem in research on dynamic networks is the issue of efficient navigation techniques in such networks. For dynamic networks, because there is still no widely developed theoretical background to understand deeply the problems, research traditionally tends to propose heuristic solutions. In the context of DTNs, these solutions tend to answer to some specific questions about navigating in a dynamic network (e.g., how to reduce energy consumption of routing, how to maximize the delivery probability) while usually ignoring and not leveraging on the profound structural properties of the dynamic network. In this work, we aim to contribute to understanding the impact of this dynamic structure on information routing and show how to exploit this structure for efficient navigation in such networks.

Compared to wired networks, Delay/Disruption Tolerant Networks (DTN) are challenging to monitor due to their lack of infrastructure and the absence of end-to-end paths. This work studies the feasibility, limits and convergence of monitoring such DTNs. More specifically, we focus on the efficient monitoring of intercontact time distribution (ICT) between DTN participants. Our contribution is two-fold. First we propose two schemes to sample data using monitors deployed within the DTN. In particular, we sample and estimate the ICT distribution. Second, we evaluate this scheme over both simulated DTN networks and real DTN traces. Our initial results show that (i) there is a high correlation between the quality of sampling and the sampled mobility type, and (ii) the number and placement of monitors impact the estimation of the ICT distribution of the whole DTN.

The small-world phenomenon first introduced in the context of static graphs consists of graphs with high clustering coefficient and low shortest path length. This is an intrinsic property of many real complex static networks. Recent research has shown that this structure is also observable in dynamic networks but how it emerges remains an open problem. In this paper, we propose a model capable of capturing the small-world behavior observed in various real traces. We then study information diffusion in such small-world networks. Analytical and simulation results with epidemic model show that the small-world structure increases dramatically the information spreading speed in dynamic networks.

This paper introduces a Swarm-Intelligence based Routing protocol (SIR) that aims to efficiently route information in content centric Delay Tolerant Networks (CCDTN) also dubbed pocket switched networks. First, this paper formalizes the notion of optimal path in CCDTN and introduces an original and efficient algorithm to process these paths in dynamic graphs. The properties and some invariant features of these optimal paths are analyzed and derived from several real traces. Then, this paper shows how optimal path in CCDTN can be found and used from a fully distributed swarm-intelligence based approach of which the global intelligent behavior (i.e. shortest path discovery and use) emerges from simple peer to peer interactions applied during opportunistic contacts. This leads to the definition of the SIR routing protocol of which the consistency, efficiency and performances are demonstrated from intensive representative simulations.

WIMAX (Worldwide Interoperability for Microwave Access) is a promising new networking technology that potentially offers high speed and wide area wireless access services that complement consistently the 3G and WiFi access networks capabilities. The standard proposes an adaptive modulation scheme which allows WiMax nodes to communicate from various modulation coding schemes according to the link quality. However, the standard does not define a detailed link adaptation algorithm and currently, the most largely used modulation adaptation technique is based on a channel quality lookup table. We argue that this method is not able to make the best adaptation decisions and delivers a sub-optimal goodput in numerous communication contexts. In this paper, we propose a novel cross layer based modulation adaptation mechanism which incorporates the use of adaptive erasure code with the physical layer information to significantly improve the goodput and transmission efficiency. Simulation results show that our proposal adapts more efficiently to real environments and achieves a significant gain on the goodput delivered to mobile nodes.

Congestion control is a fundamental mechanism for the stability of the Internet and is a central mechanism for TCP. However, this congestion control mechanism focuses mainly on the core network state and is blind to the characteristics of wireless and mobile access networks. Moreover, TCP window bas

Based on an identification and evaluation of the subtle counterproductive interactions between the WLANs MAC layer and the transport layer, this paper shows a new approach towards congestion control for WLANs. We introduce a specialization of TFRC (MTFRC: mobile TFRC), which is adapted to wireless access networks. This TFRC specialization requires only slight changes to the standard TFRC protocol. Simulation results show substantial improvements for applications over TFRC in scenarios where the bottleneck situates on the MAC layer of the mobile nodes.

The features of mobility, which enormously impact on how communication is evolving into the future, represent a particular challenge in todaypsilas wireless networking research. After an identification and evaluation of the gap between the discontinuities of the communication service inherent to the physical layer of mobile networks and the continuity requirements issue from the stream centric multimedia applications, we propose a novel middleware 3MOI (Middleware for the Mobility Management Over the Internet) which can support efficient and context-aware mobility management and satisfy new mobility requirements such as dynamical location management, fast handover, and continuous connection support.

Pervasive communications are increasingly sent over mobile devices and personal digital assistants. This trend has been observed during the last football world cup where cellular phones service providers have measured a significant increase in multimedia traffic. To better carry multimedia traffic, the IETF standardized a new TCP Friendly Rate Control (TFRC) protocol. However, the current receiver-based TFRC design is not well suited to resource limited end systems. We propose a scheme to shift resource allocation and computation to the sender. This sender based approach led us to develop a new algorithm for loss notification and loss rate computation. We demonstrate the gain obtained in terms of memory requirements and CPU processing compared to the current design. Moreover this shifting solves security issues raised by classical TFRC implementations. We have implemented this new sender-based TFRC, named TFRCught, and conducted measurements under real world conditions.

In the context of a reconfigurable transport protocol, this paper introduces two protocol instances based on the composition and specialisation of the TFRC congestion control and Selective Acknowledgment mechanisms. The two resulting transport architectures lead respectively to the QTPAF protocol, specifically designed to operate over QoS-enabled networks and the QTPlight protocol, specifically designed for resource-limited end systems connected to powerful servers. QTPAF combines QoS-aware TFRC congestion control with full reliability to provide a transport service similar to TCP but additionally taking into account network-level bandwidth reservations. QTPlight proposes a modification of TFRC that shifts from the receiver to the sender the complexity of the loss rate estimation mechanism. This modification allows to alleviate the processing and communication load of "light" resource limited mobile receivers. We present the concept of these protocols and their adaptation in the EuQoS European project framework.

In the next generation Internet, the network should evolve from a plain communication medium into an endless source of services available to the end-systems. We name these services "overlay applications". They would be composed of multiple cooperative distributed application elements that would build a dynamic communication mesh, namely "overlay association". In a former contribution, we proposed an unstructured super-peer architecture (SPAD) that provides enhanced quality of service (QoS) between end-points within an overlay association. This architecture aims at discovering and utilizing composite alternate end-to-end paths that experience better QoS than the path given by the default IP routing mechanisms. This paper presents a proactive information dissemination scheme that complements SPAD's mechanisms and significantly improves its performances.

In the next generation Internet, the network should evolve from a plain communication medium into an endless source of services available to the end-systems. These services (i.e. Overlay Applications) would be composed of multiple cooperative distributed software elements that would build dynamic communication mesh (i.e. an Overlay Association). We propose an unstructured Super-Peer architecture (SPAD) to provide enhanced Quality of Service (QoS) between end-points within an Overlay Association.

Face to the complexity involved in the wide deployment of QoS network services as well as the reduced set of services offered by existing transport protocols, this paper proposes a QoS-oriented transport protocol (QoSTP) as the adequate solution for providing soft QoS guarantees to common Internet users for next few years. The design of this QoSTP is based on a set of fundamental principles aimed at assuring the feasibly and efficient deployment of adequate mechanisms intended to satisfy different applications requirements. Moreover, this new protocol has to be designed within an extensible and compositional architectural aimed at integrating further mechanisms intended to satisfy new requirements and to operate under heterogeneous network environments. This paper presents the UML 2.0 specification model of this advanced architecture as well as experimental results intended to demonstrate the feasibility and the advantages of this approach.

Transport protocols implement mechanisms intended to satisfy the requirements of distributed applications making use of available network services. But the multiplicity of network services and the diversity of quality of service (QoS) requirements of current multimedia applications, make that efficient deployment of transport services becomes a complex function to be performed. The fully programmable transport protocol (FPTP) is a configurable and object-oriented protocol based on a compositional architecture of transport mechanisms suited to the provision, control, and management of the QoS. FPTP offers a partially ordered, partially reliable, congestion controlled and time controlled end-to-end communication service. FPTP services are intended to be easily used by legacy and specialized multimedia applications over heterogeneous transport and network services. In this paper, the unified modelling language (UML) and the specification and description language (SDL) have been used to design this transport protocol within a global QoS framework. Some study cases related to the configurable congestion control policies and aimed to demonstrate the advantages this proposal presented.

We present the idea of a programmable structured P2P architecture. Our proposed system allows the key-based routing infrastructure, which is common to all structured P2P overlays, to be shared by multiple applications. Furthermore, our architecture allows the dynamic and on-demand deployment of new applications and services on top of the shared routing layer.

The paper assesses the potential of Java for developing both portable and efficient communication software. Specifically, this paper presents and compares implementation of a multimedia transport protocol, POC, using the Java and C languages. Performances measurement are applied to the transport of MPEG streams.

A partial order and partial reliable connection (POC) is an end-to-end transport connection authorized to deliver objects in an order that can differ from the transmitted one. The service that this connection provides is also authorized to lose a number of objects. The POC approach establishes a conceptual link between both connectionless best-effort (CL) and connection oriented (OC) protocols. This approach is motivated by the fact that heterogeneous CL networks such as the Internet are plagued by unordered delivery of packets and losses, which tar the performances of current protocols. Moreover, it has been showed, in several research works, that out of order delivery is able to alleviate the use of network resources such as memory and bandwidth, and reduces end-re-end transit delay. But, in order to take advantage of these benefits, applications must be able to relax some transport constraints. A temporal extension of POC, called TPOC (for Temporal POC), is introduced. TPOC offer a conceptual framework, which allow the QoS of distributed multimedia applications to be fully taken into account. The architecture for offering a TPOC transport service is introduced and evaluated for the transport of MPEG video streams. The authors demonstrate that POC connections fill not only the conceptual gap between CL protocols (such as UDP) and OC protocols (such as TCP) but also provides real performances improvements for the transport of multimedia streams such as MPEG video.

The paper introduces a unified formal model for the complete and accurate specification of both temporal and logical (i.e., link) synchronization within hypermedia distributed and weakly synchronous systems. This new model extends time Petri nets with hierarchical design capabilities and new firing rules. These new firing rules enlighten the notion of hypermedia synchronization through powerful combinations of temporal and logical synchronization. Moreover, the proposed model offers an easy and concise modeling technique of asynchronous events in hypermedia systems.