Dissertations / Theses on the topic 'Commutation de paquets – Migration'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Commutation de paquets – Migration.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Silva, Clay Palmeira Da. "The CUBE : a user-centric system-model architecture for web service migration through multiple devices." Electronic Thesis or Diss., Tours, 2019. http://www.theses.fr/2019TOUR4041.
Full textWithin the trend of the Internet, we start to rely our daily activities on Cloud Base Systems to store our data and keep tracking all our state and behavior while using Web Services. Therefore, our data are no longer safe as before since we have delegated the responsibility to keep them safe, secure, and stored by third-party providers. In the last few years, big companies such as Yahoo, Facebook, or LinkedIn were victims of several leaks, which demonstrates how vulnerable we are. We have nowadays more powerful mobile devices than ever before. However, we do not explore their capacities regarding processing, storage, and security measures to using Web Services locally. Moreover, our devices are basically divided into two different worlds, those with Android, and those with an iOS operating system. Nevertheless, with the popularity of mobile technology, our behavior has changed. Today it is common to find a user using two or three mobile devices at the same time, and often they have a different operating system. Therefore, we are facing simultaneously a multiple-device environment with the same or different operating systems, where most of the technology and Web Services requiring a third-party provider to synchronizing and keep the state of our daily tasks. Although of this chaotic scenario regarding multiples devices and operating systems, there is a technology earlier mentioned at the end of 90's called Liquid Software that may be a solution to bring harmony to this scenario. The Liquid Software aims to allow for fluently migrate towards different devices with or without the same operating system, and at the same time keep the user-experience of a given application or service. In this thesis, based on Liquid Software principles, we focus on multiple devices environment able to synchronize Web Service at the client-side without depending on a Cloud Base System. We proposed the model-based architecture, called the CUBE, that makes use of User-Centric principles combined with different technologies, such as REST and RESTful principles. The CUBE also proposes a four layers model where REST and RESTful work independently from each other but in cooperation. Another critical element of the CUBE is the Conversation Layer (CL), modeled with the purpose to allow change data/state from Web Services. The CL makes use of techniques of Natural Language Processing to find and defining suitable Web Services to the user. Another contribution of the CUBE is creating a kind of user-network called INNER CUBE with all mobile devices that belong to a single user. The aim of combining these elements inside a single unit, the CUBE, is to allow for fluently move services/data and sessions from devices (desktops, laptops, and mobiles phones) to other ones regardless of their operating system, and at the same time, entirely transparent for the final user, and also reducing the dependency of the third-party provider. We have also proposed two tests to validate the CUBE model
Mével, Yves. "Étude d'une cellule acousto-optique à multi-transducteurs : Application à un dispositif de commutation de paquets optiques." Brest, 2003. http://www.theses.fr/2003BRES2025.
Full text@This work deals with the theoretical study and experimental characterisations of an optical packet switch for telecommunication networks at a 1. 55 æm wavelength. This switch is based on acousto-optic interaction. This manuscript is decomposed in four parts: the presentation of different technologies of optical packet switching ; the remind of the physic of acousto-optic deflexion and all critical parameters of our component ; the study of two different architectures, and the conception of a component in which two deflectors are created and superimposed applying simultaneously two RF signals on a phased array transducers. An acousto-optic switch have been built with Paratellurite TeO2. The static performances of this component were evaluated on an experimental set-up ; the measurements make appear an important signal to noise ratio (SNR) and a low dependence according to the optical polarisation
Jelassi, Ons. "Algorithmes de classement de paquets." Evry, Institut national des télécommunications, 2008. http://www.theses.fr/2008TELE0029.
Full textBaccelli, Emmanuel. "Routage et mobilité dans les grands réseaux hétérogènes à commutation de paquets." Phd thesis, Ecole Polytechnique X, 2006. http://pastel.archives-ouvertes.fr/pastel-00001603.
Full textHoll, Thomas. "Transport à fiabilité partielle d'images compresséessur les réseaux à commutation de paquets." Phd thesis, Université Henri Poincaré - Nancy I, 2007. http://tel.archives-ouvertes.fr/tel-00168798.
Full textnatures variées, ces transmissions reposent presque toujours sur TCP ou UDP. L'adoption d'une approche de
bout en bout impose d'agir sur le service de transport pour s'adapter aux besoins des données en fonction
de la qualité de service offerte par le réseau. Les données multimédias en général sont tolérantes aux
pertes, elles peuvent alors faire l'objet d'une compression et d'un transport avec pertes tout en conservant une bonne qualité de l'information reconstruite si les informations perdues sont parfaitement contrôlées.
Cela suppose que les applications multimédias puissent compter sur un service de transport adapté à leurs
besoins, associant les principes de fiabilité partielle et le contrôle d'erreur déterministe.
Dans cette thèse, nous définissons un service de transport à fiabilité partielle de ce type, utilisé pour la
transmission d'images fixes compressées sur les réseaux de type « best-effort ». Les travaux portent sur
la conciliation du transport à fiabilité partielle avec les données compressées ainsi que la recherche d'un
gain de temps de service et d'une dégradation acceptable. Un protocole de transport appelé 2CP-ARQ est proposé à cet effet. Sa compatibilité avec le transport d'images codées selon le standard JPEG2000 est d'abord étudiée. Les résultats de cette étude nous conduisent à élaborer un schéma de compression et
d'organisation des données plus approprié à l'utilisation d'un système de transport à fiabilité partielle basé
sur 2CP-ARQ. Les résultats montrent que le réseau peut bénéficier de l'utilisation de ce service de transport,
qui se traduit par une moindre sollicitation des ressources du réseau, tout en satisfaisant les contraintes de l'application en termes de qualité des images reconstruites.
Tebbal, Hassen. "Réseau local supportant un système d'exploitation distribué." Paris 9, 1986. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1986PA090048.
Full textTo realize a distributed operating system with all problems about the functionalities, we must have good network architecture. This architecture (logical) have to permit to do the integrated services of communication mixing the transmissions of data, voice and animated pictures, texts, with communication functions agreed with standard norms connection norms. The choice of network topologies and the medium are very important, they facility the transmission available in pacquet switching and circuit switching
Rampone, Thierry. "Etude d'amplificateurs optiques à semi-conducteur comme composants multifonctions pour le routage de données : conception et évaluation d'un commutateur 2 vers 2." Brest, 1997. http://www.theses.fr/1997BRES2029.
Full textNaciri, Youssef. "Synchronisation de paquets optiques dans les réseaux de télécommunications : réalisation d'un module exploitant l'interaction acousto-optique." Brest, 2000. http://www.theses.fr/2000BRES2050.
Full textHoll, Thomas. "Transport à fiabilité partielle d'images compressées sur les réseaux à commutation de paquets." Nancy 1, 2007. https://tel.archives-ouvertes.fr/tel-00168798.
Full textAlthough data can have various and multiple constraints, their transport over the Internet are based on TCP and UDP almost exclusively. The end-to-end approach enables the transport service adaptation according to the type of data as a function of the quality of service provided by networks. Generally speaking, multimedia data are loss-tolerant, so it can afford lossy compression without compromising further human interpretation after reconstruction if the lost piece of information are well controlled. This requires a transport service well suited for the needs of the multimedia applications, with the association of the partial reliability concept and deterministic error recovery mechanisms. In this thesis we proposes a partially reliable transport service intended to the transmission of compressed still images over best effort networks. We aim to find a tradeoff between the saving of time and the degradation enabled by the partial reliability. A partially reliable service called 2CP-ARQ is presented for that purpose. First, the compliance of 2CP-ARQ with the JPEG2000 standard has been studied. It shows the need to develop a compression scheme that produces independent units suited for packet encapsulation by the transport layer. It leads to the development of a compression scheme 2CP-ARQ conscious in order to satisfy the requirements of the partially reliable service but also that benefits from it. Results show that 2CP-ARQ transport service reduces the network resources consumption while the quality degradation for the reconstructed images can be bounded
Ribeiro, Cassilda. "Une methode parallele pour le routage dans les reseaux a commutation de paquets." Toulouse, INSA, 1991. http://www.theses.fr/1991ISAT0019.
Full textChaitou, Mohamad. "Performance of multicast packet aggregation with quality of service support in all-optical packet-switched ring networks." Evry, Institut national des télécommunications, 2006. http://www.theses.fr/2006TELE0007.
Full textThe explosive growth of the Internet Protocol (IP)-based traffic has accelerated the emergence of wavelength division multiplexing (WDM) technology. In order to provide a simple transport platform of IP traffic over WDM structure, optical packet switching (OPS), based on fixed-length packets and synchronous node operation, is regarded as a long term issue especially for metropolitan area networks (MANs) where the synchronization is easy to handle and relatively simple to maintain. In this context, this thesis presents a novel approach for efficiently supporting IP traffic with several quality of service (QoS) requirements into a synchronous WDM MAN layer. The claimed efficiency is achieved by aggregating IP packets regard-less of their final destinations which yields a multicast optical packet. To support QoS, a timer mechanism is used and a class-based scheme at the edge of optical network is adopted. Several analytical models have been developed to quantify the performance of different versions of the aggregation approach. The different versions correspond to different timer mechanisms and to the permission or the ban of IP packet segmentation by the aggregation process. This is because IP packets have variable size while optical packet is of fixed size. The length variability of IP traffic is included in the analytical models which represents an essential contribution of this thesis. We next investigate the impact of multicast on WDM slotted ring MANs. In particular we focus on two families of MANs. The first family enables destination stripping, while in the second one, ring nodes contain passive components and the stripping is attributed to the hub which separates two different sets of wave-length channels, one for transmission and one for reception. The capacity (maximum throughput) of each network is evaluated by means of an analytical model. The access delay is also investigated by using an approximate approach in the case of destination stripping and an exact approach in the case of hub stripping. Further-more, the impact of the optical packet format on the performance is depicted. We show the attractiveness of the multicast aggregation in MANs through a comparative study with the performance of unicast aggregation and no aggregation approaches therein. Multicast aggregation increases bandwidth efficiency due to the filling ratio improvement exhibited in optical packets. Furthermore, hub stripping networks match very well the multicast nature of the generated optical packets without the addition of any complexity in the node architecture. However, a small overhead complexity is added in the case of destination stripping networks. Note that all approximative analytical models have been validated by using extensive simulations, where two traffic profiles were investigated: Poisson and Self-Similar
Teimoori, Hassan. "Commutation de paquets dans les réseaux optiques transparents à partir de fonctions logiques tout optiques." Phd thesis, Télécom ParisTech, 2007. http://pastel.archives-ouvertes.fr/pastel-00003084.
Full textTeimoori, Hassan. "Commutation de paquets dans les réseaux optiques transparents à partir de fonctions logiques tout-optiques /." Paris : École nationale supérieure des télécommunications, 2008. http://catalogue.bnf.fr/ark:/12148/cb412463033.
Full textSamoud, Wiem. "Analyse de performance d'un commutateur de paquets hybride opto-électronique." Thesis, Paris, ENST, 2016. http://www.theses.fr/2016ENST0058/document.
Full textMost transmission systems are based on optical fibers, carrying the traffic at a relatively low energy per bit. However, due to the lack of mature optical buffers, packet switching is still performed electrically. The required Optical-Electrical-Optical (O-E-O) conversions make the switching one of the areas with the fastest-growing energy consumption. A major challenge that must be met in designing future optical networks is curbing their energy consumption. Therefore, within this thesis, we investigate a hybrid optoelectronic switch which consists of an optical switching matrix supplemented with a shared electronic buffer. Performance analysis taking into account different classes of service, packet classifications and switch connectivity methods (WDM and/or SDM channels), shows that, thanks to the established switching strategies, the hybrid switch satisfies the requirements of all the different classes of service in terms of Packet Loss Rate, sustainable system load and latency. Moreover, it significantly reduces the O-E-O conversions compared to commercial off-the-shelf electrical switches, since they occur only for buffered packets. We defend that the hybrid opto-electronic packet switch meets the requirements on quality of service and could be a promising solution to reduce the energy consumption of optical networks
Kotuliak, Ivan. "Feasibility study of optical packet switching network : performance evaluation." Versailles-St Quentin en Yvelines, 2003. http://www.theses.fr/2003VERS0021.
Full textOptical technology supplies capabilities necessary to create an optical packet switching network providing large bandwidth, high-speed data transmission and service differentiation. The aim of this thesis work is a logical performance analysis of optical packet-switching network. Studied network is based on the synchronous optical packet switching. Main part of this work deals with the analysis of two architectures: interior switch and access node. Two interior node architectures are proposed: a memory less switch and switch incorporating memory buffers based on the fiber delay lines. The access node is studied with focus on its ingress functions. Two algorithms of optical packet creation are considered: assembly and segmentation. Performance of proposed nodes is evaluated using simulation tool and discrete-time Markov chain. We show that optical packet switching network performs very well under different conditions and it is one of the promising solutions for the future high-speed networks
Hmida, Haithem. "Utilisation du protocole SNMP pour la gestion à distance d'une interface radio par paquets." Sherbrooke : Université de Sherbrooke, 1998.
Find full textArya, Vijay. "Congestion inference and traffic engineering in networks." Nice, 2005. http://www.theses.fr/2005NICE4079.
Full textThis thesis presents methods which help to improve the quality of congestion inference on both en-to-end paths and internal network links in the Internet and a method which help to perform multicast traffic engineering in Overlay Networks. First, we propose an explicit loss differentiation scheme which allows unreliable transport protocols to accurately infer congestion on end-to-end paths by correctly differentiating congestion losses from wireless losses. Second, we present two contributions related to Multicast-based Inference of Network Characteristics (MINC). MINC is a method of performing network tomography which infers loss rates, i. E. , congestion on internal network links from end-to-end multicast measurements. We propose a statistical verification algorithm which can verify the integrity of binary multicast measurements used by MINC to perform loss inference. This algorithm helps to ensure a trustworthy inference of link loss rates. Next, we propose an extended MINC loss estimator which can infer loss rates of network links using aggregate multicast feedbacks. This estimator can be used to perform loss inference in situations where the bandwidth to report multicast feedbacks is low. Third, we present efficient ways of encoding multicast trees within data packets. These encodings can be used to perform stateless and explicit multicast routing in overlay networks and thus achieve goals of multicast traffic engineering
Alhafez, Nizar. "Etude et mise en oeuvre de routages non blocants dans les architectures multi-processeurs." Lyon 1, 1991. http://www.theses.fr/1991LYO10243.
Full textEido, Thaere. "Evaluation de performance, allocation de ressources et qualité de service dans les réseaux optiques multiservices à commutation de paquets." Paris 6, 2008. http://www.theses.fr/2008PA066584.
Full textAbdellatif, Slim. "Contribution à la modélisation et à l'analyse de la qualité de service dans les réseaux à commutation de paquets." Toulouse 3, 2002. http://www.theses.fr/2002TOU30041.
Full textCharlery, Hervé Robert. "Integration d' un micro-réseau à commutation de paquets dans un système multiprocesseur à mémoire partagée intégré sur puce." Paris 6, 2005. http://www.theses.fr/2005PA066486.
Full textBoulos, Fadi. "Transmissions d'images et de vidéos sur réseaux à pertes de paquets : mécanismes de protection et optimisation de la qualité perçue." Nantes, 2010. https://tel.archives-ouvertes.fr/tel-00473801.
Full textMultimedia traffic over IP has grown significantly in recent years due to the proliferation of IPTV channels and Video on Demand (VOD) services. However, the Quality of Experience (QoE) associated with multimedia services can vary dramatically because of the fluctuating Quality of Service (QoS). Improving QoS parameters or acting directly on the QoE ensures an acceptable quality level. In this thesis, we study the perceptual impact of QoE fluctuation and the possible ways of improving it. We first propose to use an exact and discrete Radon transform, the Mojette transform, as a network coding tool. Network coding aims at enhancing QoS by optimizing the use of available bandwidth. We also propose a perceptual unequal error protection method for scalable bitstreams based on the Mojette transform. Second, we study the perceptual effects of packet loss on H. 264/AVC encoded videos by means of subjective quality tests. The test results show that the spatial position of the loss in the image is important w. R. T. The overall visual quality. This leads us to conduct eye tracking tests in order to identify the regions of interest of a video sequence. We then propose perceptual unequal error protection methods on the basis of the hierarchy determined by the regions of interest. These error resilient techniques target halting the spatio-temporal error propagation using H. 264/AVC Flexible Macroblock Ordering (FMO). Performance evaluation results show that the proposed methods are efficient against packet loss occurring in the regions of interest of the video
Guerrier, Pierre. "Un réseau d'Interconnexion pour systèmes Intégrés." Paris 6, 2000. http://www.theses.fr/2000PA066199.
Full textEt-Tolba, Mohamed. "Transmission de données pour le HSDPA et étude des algorithmes HARQ." Télécom Bretagne, 2007. http://www.theses.fr/2006TELB0024.
Full textThe major evolution of UMTS (Universal Mobile Telecommunications System) in recent years is the High Speed Downlink Packet Access (HSDPA) which provides data rates up to 10 Mbps. The implementation of HSDPA includes multicode transmission in joint application with Adaptive Modulation and Coding (AMC) as well as Hybrid Automatic Repeat reQuest (HARQ). This thesis deals with the implementation of the HSDPA simulator in FDD (FrequencyDivision Duplex) mode according to 3GPP technical specifications. It also aims to study the HARQ algorithms for HSDPA. The performance of AMC is significantly degraded when higher order modulation (16-QAM) is used in a multipath environnement. Moreover, the HSDPA simulator requires a very long time of computation to provide good performance in multipath channel. In order to solve this problem, we have introduced a simplified simulator which exploits the performance of HSDPA over gaussien channel as look-up tables to compute the block error rate in multipath channel. To make the AMC technique more powerful, we have implemented the HARQ technique. It combines ARQ methods with turbo coding. There are two fundamental approaches for HARQ : the first is Chase approach in which retransmissions are identical to the original transmission, the second approach is IR (Incremental Redundancy) in which the retransmissions carry additionnal redundancy. The performance analysis shows that a significant gain is offered by HARQ after only 2 transmissions. However this technique can exhibit an error floor when using higher order modulation in multipath environnement. As a solution to this limitation, we have employed HARQ technique combined with soft Multipath Interference Cancellation (MPIC). For enhancing this method, we have proposed to use the constellation rearrangement technique which provides additionnal diversity by changing the constellation from one transmission to other. With this techniques, very good performance is offered, and the error floor is mitigated or completely removed
Nguyen, Viet Hung. "Performance study on multi-service optical metropolitan area network : MAC protocols and quality of service." Evry, Institut national des télécommunications, 2006. https://pastel.archives-ouvertes.fr/tel-00011140.
Full textL'émergence récente de nouveaux services " paquets " (e. X. Télévision à la demande, sauvegarde des données d'entreprise. . . ) a entraîné une augmentation sans précédent des demandes de bande de passante et de qualité de service (QoS) dans les réseaux métropolitains. Les opérateurs devront remplacer leurs anciennes infrastructures des réseaux MAN (i. E. Réseaux à commutation de circuit comme SONET/SDH) par des réseaux à commutation de paquet, qui supporteront mieux les trafics sporadiques tels que vidéo et données. Cette thèse est dédiée aux études sur la nouvelle génération des réseaux métropolitains multiservices à commutation de paquet optique. Nos études se sont concentrées sur les performances logiques des protocoles d'accès (MAC) et la faisabilité de transporter les circuits TDM classiques sur un réseau en anneau à commutation de paquet optique (Optical Packet Switching Ring - OPSR). En réalité, les réseaux OPSR, qui combinent la flexibilité et la mise à l'échelle de la technologie de commutation de paquet avec les avantages de la topologie en anneau tels que la restitution rapide du service en cas de panne et un bon gain de multiplexage statistique du trafic, promettraient une bonne solution pour les réseaux MAN du future. Nous avons d'abord proposé un modèle analytique, basé sur la théorie des files d'attente avec priorité, pour évaluer la performance d'un réseau OPSR employant le protocole d'accès CSMA/CA optique asynchrone (OU-CSMA/CA). Les résultats de cette étude nous ont permis d'identifier deux défauts principaux d'un tel réseau : la non-équité entre les nœuds de l'anneau à cause de la priorité positionnelle et la fragmentation de la bande de passante à cause des transmissions asynchrones. Ces deux défauts dégradent la performance du réseau. Afin d'améliorer la performance du réseau étudié, nous avons proposé deux nouveaux mécanismes d'accès. Le premier est Modified Packet Bursting (MPB), qui augmente l'efficacité de transmission du réseau (donc, le taux d'utilisation des ressources) grâce à la suppression des en-têtes optiques inutiles. En effet, MPB concatène des paquets électroniques ayant la même destination et les envoyer avec un seul en-tête optique. Le deuxième mécanisme est Dynamic Intelligent Medium Access Control (DI-MAC), qui essaie de résoudre les problèmes identifiés cidessus dans le réseau considéré. DI-MAC utilise un algorithme distribué pour espacer dynamiquement la transmission des paquets d'un nœud en amont, afin de ne pas fragmenter la bande de passante. Par conséquent, il réserve plus de bande de passante utilisable pour les nœuds en aval. L'évaluation de performance de ces mécanismes nous a montré qu'ils améliorent considérablement la performance du réseau (beaucoup plus élevée que celles obtenues avec OUCSMA/ CA), en termes d'un taux élevé d'utilisation des ressources ainsi que de bons paramètres de performance (e. X. Délai, perte). En plus, ils rendent le réseau plus stable et quasiment insensible aux différentes configurations et au changement de trafic. Enfin, pour garantir une qualité de service équivalente à celle des réseaux TDM classiques, nous avons introduit la technologie d'émulation de circuit (CES), (qui est en cours d'être standardisée par IETF, MEF, ITU. . . ), dans le réseau OPSR en question. Nous avons étudié la faisabilité de transporter le trafic TDM dans l'OPSR, avec l'aide des mécanismes d'accès comme MPB et DI-MAC, ainsi que l'impact de CES sur la qualité de service d'autres classes de service dans le réseau. Ctions
Koubaa, Anis. "Gestion de la qualité de service temporelle selon la contrainte (m,k)-firm dans les réseaux à commutation de paquets." Vandoeuvre-les-Nancy, INPL, 2004. http://www.theses.fr/2004INPL087N.
Full textThis work focuses on the definition of a novel approach of real-time QoS using the (m,k)-firm constraints into packet switched networks. We define the concept of loss-tolerant QoS with graceful degradation that consists in guaranteeing an acceptable level of QoS for loss-tolerant real-time applications in overload situation. Our approach is mainly applied to multimedia networks assuring the delivery of real-time loss-tolerant multimedia flows such as MPEG video broadcast, Voice over Ir, audio streams. . . The contribution presented in this work is (1) to propose a novel scheduling algorithm to provide loss-tolerant QoS with graceful degradation, (2) validate the proposai through different and complementary techniques: mathematical analysis, simulation and implementation in test bed platform. Our approach of gracefully degraded QoS is based two concepts: (1) Bandwidth guarantee, (2) meeting the (m,k)-firm timing constraints. We have combined both concept to propose our scheduling algorithm, called (m,k)-WFQ, that performs fair resources sharing as dos WFQ while taking into account the (m,k)-firm timing constraints of each stream
Ben, M'Sallem Yousra. "Commutation de packets optiques avec reconnaissance des étiquettes de poids-2 par mélange à quatre ondes." Thesis, Université Laval, 2008. http://www.theses.ulaval.ca/2008/25914/25914.pdf.
Full textDias, De Amorim Marcelo. "Distribution de flux en couches dans les réseaux multicast hétérogènes." Versailles-St Quentin en Yvelines, 2001. http://www.theses.fr/2001VERS009V.
Full textHe, Peng. "Conception et évaluation des systèmes logiciels de classifications de paquets haute-performance." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAA007/document.
Full textPacket classification consists of matching packet headers against a set of pre-defined rules, and performing the action(s) associated with the matched rule(s). As a key technology in the data-plane of network devices, packet classification has been widely deployed in many network applications and services, such as firewalling, load balancing, VPNs etc. Packet classification has been extensively studied in the past two decades. Traditional packet classification methods are usually based on specific hardware. With the development of data center networking, software-defined networking, and application-aware networking technology, packet classification methods based on multi/many processor platform are becoming a new research interest. In this dissertation, packet classification has been studied mainly in three aspects: algorithm design framework, rule-set features analysis and algorithm implementation and optimization. In the dissertation, we review multiple proposed algorithms and present a decision tree based algorithm design framework. The framework decomposes various existing packet classification algorithms into a combination of different types of “meta-methods”, revealing the connection between different algorithms. Based on this framework, we combine different “meta-methods” from different algorithms, and propose two new algorithms, HyperSplit-op and HiCuts-op. The experiment results show that HiCuts-op achieves 2~20x less memory size, and 10% less memory accesses than HiCuts, while HyperSplit-op achieves 2~200x less memory size, and 10%~30% less memory accesses than HyperSplit. We also explore the connections between the rule-set features and the performance of various algorithms. We find that the “coverage uniformity” of the rule-set has a significant impact on the classification speed, and the size of “orthogonal structure” rules usually determines the memory size of algorithms. Based on these two observations, we propose a memory consumption model and a quantified method for coverage uniformity. Using the two tools, we propose a new multi-decision tree algorithm, SmartSplit and an algorithm policy framework, AutoPC. Compared to EffiCuts algorithm, SmartSplit achieves around 2.9x speedup and up to 10x memory size reduction. For a given rule-set, AutoPC can automatically recommend a “right” algorithm for the rule-set. Compared to using a single algorithm on all the rulesets, AutoPC achieves in average 3.8 times faster. We also analyze the connection between prefix length and the update overhead for IP lookup algorithms. We observe that long prefixes will always result in more memory accesses using Tree Bitmap algorithm while short prefixes will always result in large update overhead in DIR-24-8. Through combining two algorithms, a hybrid algorithm, SplitLookup, is proposed to reduce the update overhead. Experimental results show that, the hybrid algorithm achieves 2 orders of magnitudes less in memory accesses when performing short prefixes updating, but its lookup speed with DIR-24-8 is close. In the dissertation, we implement and optimize multiple algorithms on the multi/many core platform. For IP lookup, we implement two typical algorithms: DIR-24-8 and Tree Bitmap, and present several optimization tricks for these two algorithms. For multi-dimensional packet classification, we have implemented HyperCuts/HiCuts and the variants of these two algorithms, such as Adaptive Binary Cuttings, EffiCuts, HiCuts-op and HyperSplit-op. The SplitLookup algorithm has achieved up to 40Gbps throughput on TILEPro64 many-core processor. The HiCuts-op and HyperSplit-op have achieved up to 10 to 20Gbps throughput on a single core of Intel processors. In general, our study reveals the connections between the algorithmic tricks and rule-set features. Results in this dissertation provide insight for new algorithm design and the guidelines for efficient algorithm implementation
Boyer, Florence. "Conception et routage dans les réseaux de télécommunication." Clermont-Ferrand 2, 1997. http://www.theses.fr/1997CLF21981.
Full textBenaïssa, Mouna. "Ajustement dynamique du délai de présentation des paquets pour le transport de la voix dans les réseaux ad hoc." Nancy 1, 2004. http://www.theses.fr/2004NAN10029.
Full textErrors treated in voice applications include lost packets arriving with long delays. Ad hoc networks introduce random delay variations in voice applications which require low delay and no jitter. To overcome this jitter and late lost packet, a dynamic playout delay adjustment algorithm is needed. As existing algorithms do not operate correctly in ad hoc networks characterized by mobility, a new algorithm is proposed. This algorithm takes advantage of RREQ control message of AODV reactive routing protocol (a typical event in ad hoc networks) to correctly deal with topology changes. The performance evaluation showed that it reacts correctly to the mobility effects. It outperforms the existing algorithms when considering interactivity, reliability and stability constraints
Minakhmetov, Artur. "Cross-layer hybrid and optical packet switching." Electronic Thesis or Diss., Institut polytechnique de Paris, 2019. http://www.theses.fr/2019IPPAT006.
Full textTransparent optical telecommunication networks constitute a development step from all-electronic networks. Current data network technologies already actively employ optical fibers and transparent networks in the core, metro, and residential area networks. However, these networks still rely on Electronic Packet Switching (EPS) for packets routing, constituting obligatory for each packet optical-to-electronic-to-optical (OEO) signal conversion. On the other hand, Optical Packet Switching (OPS), seemed to be as replacement of EPS, has long promised performance and energy consumption improvements by going away from OEO conversions; however, the absence of practical optical buffers made OPS highly vulnerable to contention, incurring performance reduction, and getting in the way of profiting from OPS gains. The subject of this research lies in the investigation of the performance of OPS networks under all-optical and hybrid switches, while server-side transmission activities are regulated by Transport Control Protocols based on Congestion Control Algorithms (TCP CCAs). We consider that OPS could be enabled by use hybrid switch, i.e. device-level solution, as well by use of specially designed TCP CCAs, i.e. networklevel solution, giving birth to Hybrid Optical Packet Switching (HOPS) networks. We extensively study OPS, HOPS and EPS types of Data Center Networks (DCN) coupled with different TCP CCAs use by following the next three axes of DCN performance: Throughput, Energy Consumption, and Latency. As for TCP CCAs we consider not only existing but also newly developed solutions. If Stop-And-Wait (SAW), Selective Acknowledgment (SACK), modified SACK (mSACK) and Data Center TCP (DCTCP) are already known to the world, StopAnd-Wait-Longer (SAWL) is newly presented and is designed to bring the best out of the HOPS DCN. As a result, it is shown that hybrid switch solutions significantly outperform bufferless all-optical switches and reach the level of all-electronic switches in DCNs in terms of throughput. In terms of energy consumption, hybrid solutions can save up to 4 times on energy on switching compared to all-electronic solutions. As well HOPS DCNs can exhibit microseconds-scale average latencies, surpassing EPS and performing on the level with OPS. The question of the introduction of Classes of Service to HOPS DCN is also investigated: it was found that class-specific switching rules to hybrid switch can ameliorate the performance of certain classes without almost performance loss in others
Bourguiba, Manel. "Plateforme flexible et performante pour les routeurs virtuels sur une architecture multi-coeur." Paris 6, 2011. http://www.theses.fr/2011PA066237.
Full textSoëte, Thomas. "Couche logicielle bas niveau efficace pour interface radio à faisceaux agiles." Thesis, Lille 1, 2010. http://www.theses.fr/2010LIL10179/document.
Full textThe work presented in this paper are placed in the context of wireless networks without infrastructure (Ad Hoc) involving the use of sector antennas in a 60 GHz radio channel. The antenna consists of several simple antennas; each intended for a particular sector and may be mechanically switched to activate a single sector. It is thus possible to choose the area of transmitting or receiving data. This type of antenna nevertheless suffers from a problem with this mechanical switching: it cannot be done instantly. At each change of sector, a small amount of time is lost, which reduces the efficiency. This problem is particularly important when the switching time is around the time needed to send a packet: more than half of the bandwidth can be wasted. The state of the art solutions for supporting sector antennas generally do not take into account this switching time and therefore are not adapted to this problem. The thesis is that by taking into account the switching time, it is possible to produce an efficient and adapted protocol stack to this type of antennas. We therefore propose a new optimized protocol stack including the two lower layers of the OSI model. It then remains interoperable with other systems
Nott, David. "Modélisation et évaluation de performances des algorithmes liés au routage de paquets de taille fixe dans le réseau de coeur ROMéO." Versailles-St Quentin en Yvelines, 2009. http://www.theses.fr/2009VERS0039.
Full textLa technologie tout-optique représente une technologie séduisante et prometteuse pour les réseaux du futur. La faisabilité et les performances d'un réseau tout-optique ont été étudiées dans le projet ROM. Avec le tout-optique, la transmission et la commutation des paquets sont effectuées en optique. La mémoire optique n'est pas ou peu disponible. Le routage le plus étudié pour le tout-optique est le routage à déflexion qui offre un bon débit mais dont la queue de la distribution de transport n'est pas bornée. Le routage eulérien offre une garantie de terminaison au transport des paquets, mais un faible débit. Le routage mixte est une combinaison du routage à déflexion et du routage eulérien dans laquelle un paquet débute en mode déflexion, et s'il prend trop de temps pour sortir du réseau, finit son transport en mode eulérien. Cette thèse poursuit les travaux de ROM dans le projet ROMéO en considérant l'aspect routage d'un réseau tout-optique. Le premier aspect étudié porte sur l'évaluation de performance du routage à déflexion, avec comme critère de performance, la probabilité d'un paquet de subir une déflexion et la distribution du temps de transport. Le second aspect étudié porte sur le routage mixte. D'une part, nous proposons des algorithmes pour construire des circuits eulériens en abaissant la garantie de terminaison du routage mixte. D'autre part, nous mettons en évidence la vulnérabilité du routage mixte face à une congestion. Nous montrons que le débit du routage mixte baisse significativement à la suite d'une rafale de trafic et que le débit du réseau peut ne pas remonter, même après la fin de la rafale de trafic. Nous montrons qu'un contrôle d'accès à l'entrée du réseau permet de prévenir la congestion et de sortir le réseau d'une congestion
Dewolf, Tristan. "Nano-caractérisation des mécanismes de commutation dans les mémoires résistives à base d'HfO2." Thesis, Toulouse 3, 2018. http://www.theses.fr/2018TOU30223/document.
Full textDigital technology is invading our day life and the amount of data is exploding. This implies to develop memories which perform better and better. This is a major issue in microelectronics. Among non-volatile memories, Oxide based resistive RAM are particularly attractive (compatible with CMOS technology, low programming voltage) and are considered as promising candidate for replacing FLASH memories. The stack is simple (M-I-M) and the switching is based on resistance changes under an applied electrical stress. If forming and breaking a nanometer-sized conductive area is commonly accepted as the physical phenomenon involved in the switching mechanism, a debate remains about the nature and the characteristics of the filamentary area (oxygen vacancies, metallic element). Based on transmission electron microscopy methods - STEM-HAADF and STEM-EELS - this thesis work provides, at the scale of the filament (nm), a further understanding about the physico-chemical modifications of the memory cell induced by the operating step (FORMING, RESET). The TiN/Ti/HfO2/TiN stack, processed with microelectronic techniques, was incorporated into different architectures (1R, 1T1R) with a shaped top electrode (diameter 50 to 200 nm) to confine the filament in a volume compatible with TEM and then biased with different methods (C-AFM, measuring bench, in-situ TEM). When thermal effects are under control, the analysis of the EELS elementary maps shows that titanium from the top electrode plays a role in the switching mechanism (local migration in the HfO2 layer) in addition to the oxygen depletion at the HfO2/bottom electrode interface and probably at grain boundaries in HfO2
Hénocq, Xavier. "Contrôle d'erreur pour transmission de flux vidéo temps réel sur réseaux de paquets hétérogènes et variant dans le temps." Rennes 1, 2002. http://www.theses.fr/2002REN10020.
Full textElbiaze, Halima. "Application des techniques de contrôle d'accès à la garantie de QoS dans un réseau optique multiservice." Versailles-St Quentin en Yvelines, 2002. http://www.theses.fr/2002VERS004V.
Full textRaad, Robert. "Overlapped CDMA system in optical packet networks : resource allocation and performance evalutation." Doctoral thesis, Université Laval, 2009. http://hdl.handle.net/20.500.11794/20603.
Full textBen, Msallem Yousra. "Optical packet networks : enabling innovative switching technologies." Thesis, Université Laval, 2014. http://www.theses.ulaval.ca/2014/30444/30444.pdf.
Full textLarge scale computer networks require fast and reliable data links in order to support growing web applications. As the number of interconnected servers and storage media increases, optical communications and routing technologies become interesting because of the high speed and small footprint of optical fiber links. Furthermore, optical packet switched networks (OPSN) provide increased flexibility in network management. Future networks are envisaged to be wavelength dependent routing, therefore OPSN will exploit tunable wavelength converters (WC) to enable contention resolution, reduce wavelength blocking in wavelength routing and switching, and provide dynamic wavelength assignment. Optical transmitters based on multi-wavelength sources are presented as an attrative solution compared to a set of single distributed feedback lasers in terms of cost, footprint and power consumption. Wavelength converters should support high bit rates and a variety of signal formats, have fast setup time, moderate input power levels and high optical signal-to-noise ratio at the output. Several wavelength conversion technologies have been demonstrated. The use of four wave mixing (FWM) in semiconductor optical amplifiers (SOAs) provides low input power levels, acceptable conversion efficiency and the possibility of photonic integration. SOAs therefore offer excellent trade-offs compared to other solutions. To achieve wide wavelength coverage and integrability, we use a dual pump scheme exploiting four-wave mixing in semiconductor optical amplifiers. For phase stability, we use a quantum-dash mode-locked laser (QD-MLL) as a multi-wavelength source for the dual pumps, with tunability provided by the frequency selective filter. We investigate the proposed wavelength converter and compare its performance of wavelength conversion for different non-return-to-zero (NRZ) intensity and phase modulation formats at different bit rates (10 and 40 Gbit/s). Bit error rate, conversion efficiency and optical signal-to-noise ratio measurements are reported. We demonstrate the possibility of tightly packed payload and label wavelength conversion at very high data baud rate over wide tuning range with good conversion efficiency. Our demonstration concentrates on conversion performance, hence continuous payload and label signals were used without gating into packets. Bit error measurements for both payload and label were performed. We propose the use of QD-MLL as multi-wavelength source for WDM unicast and multicast applications and we investigated its compatibility with DQPSK transmission at high bit rate. We quantify DQPSK performance via bit error rate measurements and compare performance to that of an external cavity laser (ECL) source.
Chatté, Fabien. "Contribution au contrôle de congestion dans les protocoles de transport." Compiègne, 2004. http://www.theses.fr/2004COMP1514.
Full textLn this PhD thesis manuscript, we begin by presenting a panorama of different congestion control techniques implemented in unicast transport protocols. Next, we present a study in which we try to define the validity limits of the fluid approximation of a packets switched network. After, we describe and justify the development (in the continuous time domain) of a controller, which is used to compensate the sending rate of network sources in order to avoid congestions. Once the controller developed, we discretize it in order to implement it in a transport protocol. To objectively compare our congestion control mechanism to the existing ones, we define a comparison methodology. This methodology allows to evaluate performance of congestion control mechanisms. At the end, we compare the performance of our protocol with those of several existing transport protocols. This comparison allows us to analyse in several cases, the behaviour of the tested protocols
Dumas, feris Barbara Pilar. "Réseaux optiques en mode paquet pour les connexions internes à un centre de données." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2017. http://www.theses.fr/2017IMTA0057/document.
Full textData-center energy consumption is nowadays a major issue. Intra-data-center networking accounts almost for a quarter of the data-center total power consumption. Optical switching technologies could provide higher power efficiency than current solutions based on electrical-packet switching. This work focuses on optical-packet-switched networks for small- and medium-size data centers. It takes part of the EPOC (Energy-Proportional and Opportunistic Computing) project, which main interest consists on reducing the overall power consumption of a data center partially powered by renewable sources. A key assumption is that our data center does not rely on a dedicated storage network, in order to reduce the consumption of those interconnections. In addition, with the aim of being able to turn off some servers according to the workload and the available energy, the bit rate must be close to 100 Gbit/s. We have chosen, after studying the state of the art of data-center interconnects, a purely passive network architecture based on fast-wavelength-tunable transmitters under the name of POPI.We study POPI's limitations due to its components (insertion loss, tuning range and channel spacing). We then propose an extension called E-POPI that allows to increase the number of connected servers by using several transmission bands. For larger data centers, we propose POPI+, a two-stage infrastructure for intra- and inter-rack communications operating in the C and L bands, respectively. The connection between both stages is done via a transparent gateway in one direction and an opaque one in the other. We discuss different control solutions for both stages.The feasibility of these architectures depends on, among other factors, dealing with bit-rate increasing and power losses of a passive interconnect. Coherent long-distance-transmission techniques are not currently suited to data centers. We therefore studied PAM 4 and 8 modulation formats with direct detection. On one hand, by simulation, with different bit rates (up to 112 Gbit/s) and receivers (PIN, APD and SOA-PIN) and, on the other hand, experimentally, at 12 and 18 Gbit/s. We have developed a method for compensating the distortions generated by the different network components. Our method takes into account a good tradeoff between correction accuracy and computation time.Simulation results allow us to determine the amount of insertion loss that may be supported. We then combine these results with the limitations of transmitters-tuning range and channel spacing using multiple of 12.5 GHz slots for dimensioning the proposed architectures. POPI, E-POPI and POPI+ interconnects allow the connection of 48, 99 and 2352 entities, respectively, at 112 Gbit/s. Our assessments take into account a potential dispersion of the characteristics of the main architecture components
Freire, Hermelo Maria. "Amplifier control using machine learning and coloured optical packet switching node design in optical networks." Electronic Thesis or Diss., Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAS024.
Full textData rate and energy consumption are the major concerns in optical networks. In order to reduce energy consumption, transport operator networks based on optical circuit switching (OCS) concept, are becoming optically transparent, reducing optical to electrical (O/E) and electrical to optical (E/O) conversions. To face data rate increase, complex modulation formats and dual-polarization systems are considered and fiber spectrum is saved using network resources in a more efficient way, giving rise to a flexible frequency grid. Flexible transponders are developed to tune modulation formats and wavelengths and reconfigurable optical add/drop multiplexers (ROADMs) based on wavelength selective switches (WSSs) are studied. Flexible networks consider also a more dynamic traffic. Dynamism and flexibility lead to a deep transformation of the optical networks, including optical nodes, from both physical and control layer point of view. When channels are added and/or dropped, optical power excursion from erbium doped fiber amplifiers (EDFAs) has to be controlled dynamically. In that context, software defined networking (SDN) assisted by machine learning (ML) techniques is envisaged as promising candidate for the management and the dynamic control of optical networks. In this context, in the first part of our PhD work, we deal with optical power excursion in dynamic optical transport networks. In order to mitigate undesirable effects, we introduce and implement power excursion prediction and pre-compensation module using ML methods. As physical layer impairments (PLIs) accumulate along the path, we consider optical power excursion together with optical signal to noise ratio (OSNR) and bit error rate (BER), to estimate quality of transmission (QoT) of unseen channel configurations. Afterwards, using a reinforcement learning (RL) approach, we establish an autonomous impairment aware modulation format and wavelength assignment procedure, and we show that this permits to reduce the blocking probability of the incoming demands in optical nodes. In the second part of our PhD work, in the context of the N-GREEN project from the French national agency of research, we address a disruptive network architecture based on coloured optical packet switching (OPS). The main objective of N-GREEN is to propose a new generation of energy efficient routers. In the N-GREEN project, we perform the experimental characterization of an optical 2 x 2 switch based on semiconductor optical amplifiers (SOAs). This characterization leads to the proof of concept of a ring network with 10 nodes in cascade. Envisaging a 16 x 16 switch configuration, the experimental characterization, in single channel and WDM configurations, unveil interesting possibilities for the transmission of ultra-high data rates
Dridi, Khaled. "Spécification du protocole MAC pour les réseaux IEEE 802.11e à différentiation de services sous contrainte de mobilité." Thesis, Paris Est, 2011. http://www.theses.fr/2011PEST1016/document.
Full textThis thesis proposes a new approach relating to the packets scheduling algorithm, the cooperation scheme and the nodes' mobility for IEEE 802.11 wireless network family. Considering the QoS delivery process at the MAC level consists the main feature of the proposal research study. The analysis of the current mechanisms leads to keep the protocol EDCF as the basic model for our work platform. In order to overcome the weakness of the earlier 802.11 standard, a new model based on multi-scheduler algorithm, called HCF-T, is proposed. The achieved performances are summarized following several criteria: traffic control, throughput improving, collisions avoidance, and network load decreasing. Furthermore, in the way of getting better results according to the PHY layer, we presented and analyzed a model of cooperative diversity scheme. It included a couple of relaying protocols AAF and DAF supported by a set of combining techniques to backup the signal at the receiver. To support node's mobility within EDCF, we built-up a model of WLAN which able to track node motion and control the access as in real condition. In the case of overlapping APs ranges, we developed a Multi-coverage algorithm aiming to carry out the session associations. As a result, three levels (Low, Medium, and High) of node's speed are discerned. Finally, EDCF has been implemented on various static and dynamic scenarios. The performances, based on the main MAC-layer metrics, such as throughput, End-2-End delay, and jitter, have been classified and comprehensively evaluated
Chaignon, Paul. "Software Datapaths for Multi-Tenant Packet Processing." Thesis, Université de Lorraine, 2019. http://www.theses.fr/2019LORR0062/document.
Full textMulti-tenant networks enable applications from multiple, isolated tenants to communicate over a shared set of underlying hardware resources. The isolation provided by these networks is enforced at the edge: end hosts demultiplex packets to the appropriate virtual machine, copy data across memory isolation boundaries, and encapsulate packets in tunnels to isolate traffic over the datacenter's physical network. Over the last few years, the growing demand for high performance network interfaces has pressured cloud providers to build more efficient multi-tenant networks. While many turn to specialized, hard-to-upgrade hardware devices to achieve high performance, in this thesis, we argue that significant performance improvements are attainable in end-host multi-tenant networks, using commodity hardware. We advocate for a consolidation of network functions on the host and an offload of specific tenant network functions to the host. To that end, we design Oko, an extensible software switch that eases the consolidation of network functions. Oko includes an extended flow caching algorithm to support its runtime extension with limited overhead. Extensions are isolated from the software switch to prevent failures on the path of packets. By avoiding costly redirections to separate processes and virtual machines, Oko halves the running cost of network functions on average. We then design a framework to enable tenants to offload network functions to the host. Executing tenant network functions on the host promises large performance improvements, but raises evident isolation concerns. We extend the technique used in Oko to provide memory isolation and devise a mechanism to fairly share the CPU among offloaded network functions with limited interruptions
Mekbungwan, Preechai. "In-network Computation for IoT in Named Data Networking." Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS151.
Full textActiveNDN is proposed to extend Named Data Networking (NDN) with in-network computation by embedding functions in an additional entity called Function Library, which is connected to the NDN forwarder in each NDN router. Function calls can be expressed as part of the Interest names with proper name prefixes for routing, with the results of the computation returned as NDN Data packets, creating an ActiveNDN network. Our main focus is on performing robust distributed computation, such as analysing and filtering raw data in real-time, as close as possible to sensors in an environment with intermittent Internet connectivity and resource-constrained computable IoT nodes. In this thesis, the design of ActiveNDN is illustrated with a small prototype network as a proof of concept. Extensive simulation experiments were conducted to investigate the performance and effectiveness of ActiveNDN in large-scale wireless IoT networks. The real-time processing capability of ActiveNDN is also compared with centralized edge computing approaches. Finally, the ActiveNDN is demonstrated over the wireless sensor network testbed with real-world applications that provide sufficiently accurate hourly PM2.5 predictions using linear regression model. It shows the ability to distribute the computational load across many nodes, which makes ActiveNDN suitable for large-scale IoT deployments
Obenofunde, Simon. "Topology Management in wireless sensor networks." Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCK025.
Full textWireless sensor networking is ingratiating itself into almost every area of human endeavors. Its drivers include its usages, improvements in microelectronics and manufacturing techniques. The network is made up of multiple tiny sensor nodes deployed in the area to be sensed, with nodes having processing, communicating, and sensing capabilities that enable them to perform their function collaboratively. Nodes sense events and transmit their data to the sink directly or through intermediate nodes acting as relay.Despite all the tremendous advances that have been made on this technology over the past few years, energy has not kept pace. This is based mostly on the fact that battery is its main source of energy. Furthermore, some applications of the network may preclude batteries from either being recharged or changed after deployment.A renowned solution to energy efficiency is duty cycling. This is the periodic or aperiodic placing of a node in an active and an inactive state. This introduces network performance issues of availability, latency, and packet delivery ratio, all linked to the fact that once a node is inactive or off, it is unavailable to communicate. It is therefore important to look for means of still applying duty cycling yet not losing out in availability, latency, and packet delivery ratio.In this dissertation we employ duty cycle on topology management to extend the network lifetime. We propose five algorithms to build various topologies that we divide into two classes. The first class enables nodes to arrange themselves into repetitive and interleaving sets. That is, nodes in the same set repeat themselves on the ground such that a set spans the entire area to be sensed. The second class of algorithms arranges nodes in continuous successive sets with members of a set covering a transmission range. We demonstrate the set formation experimentally.Building on the continuous set formation we propose two algorithms that build disjoint virtual backbone networks, with the disjointedness used for activity scheduling. We then measure the performances of the algorithms notably the approximation ratio and find it quite low (in the order of 3.5) compared to what is obtained in the literature.Finally, we propose a sleep and relay protocol that works on these topologies. Nodes sleep in sets and the activeness is relayed between sets. We evaluate the performance of this protocol and confirm that it actually leads to increase energy savings while not deteriorating other network performance metrics, like latency and packet delivery ratio
Breck, Damien. "Évaluation des performances du système d'agrégation implémenté dans les réseaux 802.11n." Thesis, Université de Lorraine, 2015. http://www.theses.fr/2015LORR0278/document.
Full textAfter the increase of the capacity of wireless networks, the improvement of the low efficiency allows users to benefit from higher bandwidths. This improvement is partly due to the creation of aggregation's systems. Now, if these systems allow to improve the offered bandwidth, several problems arise about their influence on the behavior of the system. In particular, the case of strong competition for the access to the medium remains unknown. The aggregation studied in this thesis makes a concatenation of several packets in a single frame. This operation allows the packets to share headers. Besides the loss of meaning about the value of a packet, the configuration of such a system remains today obscure for the access provider. As the interests of the provider and its customers may differ, it is also necessary to consider a compromise between their respective requirements. To address these issues, this thesis focuses on a thorough analysis of the behavior and the implications of a packet aggregation system (with IEEE 802.11n as case study). The impact of aggregation on the quality of service provided to an application is quantified through thousands of simulations with Riverbed Modeler. Recommendations are then proposed for the proper setup of the aggregation system to optimize delay and backlog. This thesis focuses on the performances offered to a particular flow in competition for the medium. Its aim is to show the influence of the aggregation on each customer. This thesis also develops an analytical model of the aggregation system using the network calculus theory. The limitations of such a model are demonstrated. Its pessimism is determined using a detailed analysis of the 802.11n aggregation. This study demonstrates a particular relative inadequacy of network calculus to the aggregation system considered. Adjustments of the theory are then proposed, particularly for the calculation of the residuel service offered to a customer. To help the access provider in the configuration of the aggregation system, this thesis lastly proposes an algorithm for a dynamic configuration of the aggregation. This algorithm is established from the recommendations previously established. Its originality is based on the deactivation of the aggregation according to the state of the competing stations. Implemented in Riverbed Modeler, this algorithm shows its efficiency. Then, new problems arise about its real implementation (distributed, centralized, ...)
Nguyen, Alex The Phuong. "Short frame wireless communications : new challenges for the physical layer." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2019. http://www.theses.fr/2019IMTA0154.
Full textUpcoming wireless communication systems are expected to make intensive use of short packet transmission. An epitome is the emerging 5G standard, for which two out of the three principal use cases, massive Machine Type Communications (mMTC) and Ultra Reliable Low Latency Communications (URLLC), are intrinsically based on short packets. Another example is provided by the recent Low-Power Wide Area Networks (LPWAN) designed to support the IoT such as Sigfox, LoRa, etc.The use of short packets at the physical layer may substantially change the way digital communication systems are designed. In particular, at short block length, header overhead may no longer be considered negligible. More importantly, asymptotic results from information theory which have been a central guide and a key driver to the design of ever-improving communication systems so far no longer hold in this regime. How, then, to ensure reliable communication without increasing the code length since the latter is no longer an option ? By extension and more fundamentally, how to design the physical layer of short packets to ensure optimal performance with the most efficient use of available resources at hand ? The focus of this PhD thesis is to revisit physical layer design for short-packet communication and to propose new design guidelines leveraging the latest results on channel coding in the finite blocklength regime
Mokhtari, Amdjed. "ARFANet : Une nouvelle approche pour les réseaux actifs." Phd thesis, Université de Versailles-Saint Quentin en Yvelines, 2005. http://tel.archives-ouvertes.fr/tel-00010867.
Full textdes applications clientes, des protocoles, des services et des flux. Seules les couches basses restent rigides et obéissent fidèlement
à des mécanismes datant de la création du réseau Internet.
L'enjeu économique et le marché financier qui s'est tissé autour de l'infrastructure actuelle rendent difficilement le passage
à l'échelle mondiale de nouveaux protocoles.
Les réseaux actifs sont une alternative envisageable qui permet de surpasser rapidement et efficacement ce blocage en prévision de
la saturation du réseau à la suite de l'évolution incessante
de l'Internet en termes du nombre croissant d'utilisateurs et de services.
Dans un réseau actif, les traitements à effectuer dans les différents
noeuds peuvent être adaptés aux besoins de l'utilisateur et/ou de
l'application elle-même. Les fonctionnalités spécifiques à un
utilisateur ou à une application sont chargées dans les noeuds du
réseau sous forme de méthodes ou de petits
programmes. Lorsqu'un paquet de données de l'utilisateur arrive aux noeuds spécifiés, son en-tête
est évaluée et le programme approprié est exécuté sur le contenu du paquet.
Nous avons développé une nouvelle infrastructure de réseaux actifs, appelée ARFANet
(Active Rule Framework for Active Networks), basée sur la notion de règles actives.
Dans ce contexte, une application peut être décrite comme un ensemble de règles
actives, où chaque règle est définie sous la forme d'un tuple Evènement-Condition-Action (ECA).
L'exécution de l'application consiste alors à détecter les
évènements, évaluer les conditions et lancer les actions
correspondantes. La forme ECA est fondée exclusivement sur un concept événementiel et rend les règles actives des candidates
potentielles pour les applications réseau qui doivent réagir aux événements survenant au sein du réseau tels l'arrivée d'un paquet,
la formation d'un goulot d'étranglement ou d'une congestion, la rupture d'un lien, etc.
Deux aspects très importants dans les réseaux actifs et leur émergence sont la distribution
du code actif et la sécurité.
Nous avons défini la notion de serveur de code et d'identification (CISS) qui permet le stockage de code et
son identification. Avec ce serveur nous pouvons appliquer toutes les techniques de sécurité impliquant tous les acteurs
liés au processus de la distribution tels que le développeur, les utilisateurs et le code lui-même.
Les tâches de sécurité ne sont plus du ressort des noeuds mais déléguées à ce serveur, ainsi les performances des
noeuds ne sont pas altérées.
Par ailleurs nous avons constaté la nécessité d'introduire plusieurs serveurs d'identification et de stockage de code
dans les réseaux de grande envergure. La gestion de la base de codes distribuée doit prendre en compte toutes
les spécificités des réseaux actifs. Nous avons également concentré une grande partie de nos efforts à l'évaluation des performances d'un noeud de l'infrastructure
ARFANet qui nous a amenés à modéliser ce noeud, dans une première phase,
en utilisant la méthode analytique PEPA, puis le simuler, dans une seconde phase, avec l'outil SimJava.