With the advent of Smart Cities, Intelligent Transport System (ITS) has become an efficient way of offering an accessible, safe, and sustainable transportation system. Utilizing advances in Information and Communication Technology (ICT), ITS can maximize the capacity of existing transportation system without building new infrastructure. However, in spite of these technical feasibilities and significant performance-cost ratios, the deployment of ITS is limited in the real world because of several challenges associated with its architectural design. This thesis studies how to design a highly flexible and deployable architecture for ITS, which can utilize the recent technologies such as - cloud computing and the publish/subscribe communication model. In particular, our aim is to offer an ITS infrastructure which provides the opportunity for transport authorities to allocate on-demand computing resources through virtualization technology, and supports a wide range of ITS applications. We propose to use an Infrastructure as a Service (IaaS) model to host large-scale ITS applications for transport authorities in the cloud, which reduces infrastructure cost, improves management flexibility and also ensures better resource utilization. Moreover, we use a publish/subscribe system as a building block for developing a low latency ITS application, which is a promising technology for designing scalable and distributed applications within the ITS domain. Although cloud-based architectures provide the flexibility of adding, removing or moving ITS services within the underlying physical infrastructure, it may be difficult to provide the required quality of service (QoS) which decrease application productivity and customer satisfaction, leading to revenue losses. Therefore, we investigate the impact of service mobility on related QoS in the cloud-based infrastructure. We investigate different strategies to improve performance of a low latency ITS application during service mobility such as utilizing multiple paths to spread network traffic, or deploying recent queue management schemes. Evaluation results from a private cloud testbed using OpenStack show that our proposed architecture is suitable for hosting ITS applications which have stringent performance requirements in terms of scalability, QoS and latency. / Baksidestext: Intelligent Transport System (ITS) can utilize advances in Information and Communication Technology (ICT) and maximize the capacity of existing transportation systems without building new infrastructure. However, in spite of these technical feasibilities and significant performance-cost ratios, the deployment of ITS is limited in the real world because of several challenges associated with its architectural design.  This thesis studies how to design an efficient deployable architecture for ITS, which can utilize the advantages of cloud computing and the publish/subscribe communication model. In particular, our aim is to offer an ITS infrastructure which provides the opportunity for transport authorities to allocate on-demand computing resources through virtualization technology, and supports a wide range of ITS applications. We propose to use an Infrastructure as a Service (IaaS) model to host large-scale ITS applications, and to use a publish/subscribe system as a building block for developing a low latency ITS application. We investigate different strategies to improve performance of an ITS application during service mobility such as utilizing multiple paths to spread network traffic, or deploying recent queue management schemes. / <p>Artikel 4 Network Centric Performance Improvement for Live VM Migration finns i avhandlingen som manuskript. Nu publicerat konferenspaper. </p>

This thesis is concerned with the modeling and the analysis of distributedreal-time systems. In distributed systems, components evolve partlyindependently: concurrent actions may be performed in any order, withoutinfluencing each other and the state reached after these actions does notdepends on the order of execution. The time constraints in distributed real-timesystems create complex dependencies between the components and the events thatoccur. So far, distributed real-time systems have not been deeply studied, andin particular the distributed aspect of these systems is often left aside. Thisthesis explores distributed real-time systems. Our work on distributed real-timesystems is based on two formalisms: time Petri nets and networks of timedautomata, and is divided into two parts.In the first part, we highlight the differences between centralized anddistributed timed systems. We compare the main formalisms and their extensions,with a novel approach that focuses on the preservation of concurrency. Inparticular, we show how to translate a time Petri net into a network of timedautomata with the same distributed behavior. We then study a concurrency relatedproblem: shared clocks in networks of timed automata can be problematic when oneconsiders the implementation of a model on a multi-core architecture. We showhow to avoid shared clocks while preserving the distributed behavior, when thisis possible.In the second part, we focus on formalizing the dependencies between events inpartial order representations of the executions of Petri nets and time Petrinets. Occurrence nets is one of these partial order representations, and theirstructure directly provides the causality, conflict and concurrency relationsbetween events. However, we show that, even in the untimed case, some logicaldependencies between event occurrences are not directly described by thesestructural relations. After having formalized these logical dependencies, wesolve the following synthesis problem: from a formula that describes a set ofruns, we build an associated occurrence net. Then we study the logicalrelations in a simplified timed setting and show that time creates complexdependencies between event occurrences. These dependencies can be used to definea canonical unfolding, for this particular timed setting.

Multimedia services are the killer applications on next generation convergent networks. Video contents are the most resource consuming part of a multimedia flux. Video transmission, video multicast and video conferencing services are the most popular types of video communication with increasing difficulty levels. Four main parts of the distributed cross-layer scalable multimedia services over next generation convergent networks are considered in this research work, both from the architecture and performance point of views. Firstly, we evaluate the performance of scalable multimedia transmissions over an overlay network. For that, we evaluate the performance of scalable video end-to-end transmissions over EvalSVC. It is capable of evaluating the end-to-end transmission of SVC bit-streams. The output results are both objective and subjective metrics of the video transmission. Through the interfaces with real networks and an overlay simulation platform, the transmission performance of different types of SVC scalability and AVC bit-streams on a bottle-neck and an overlay network will be evaluated. This evaluation is new because it is conducted on the end-to-end transmission of SVC contents and not on the coding performance. Next, we will study the multicast mechanism for multimedia content over an overlay network in the following part of this PhD thesis. Secondly, we tackle the problems of the distributed cross-layer scalable multimedia multicast over the next generation convergent networks. For that, we propose a new application-network cross layer multi-variable cost function for application layer multicast of multimedia delivery over convergent networks. It optimizes the variable requirements and available resources from both the application and the network layers. It can dynamically update the available resources required for reaching a particular node on the ALM's media distribution tree. Mathematical derivation and theoretical analysis have been provided for the newly proposed cost function so that it can be applied in more general cases of different contexts. An evaluation platform of an overlay network built over a convergent underlay network comprised of a simulated Internet topology and a real 4G mobile WiMAX IEEE802.16e wireless network is constructed. If multicast is the one-to-many mechanism to distribute the multimedia content, a deeper study on the many-to-many mechanism will be done in the next part of the thesis through a new architecture for video conferencing services. Thirdly, we study the distributed cross-layer scalable video conferencing services over the overlay network. For that, an enriched human perception-based distributed architecture for scalable video conferencing services is proposed with theoretical models and performance analysis. Rich theoretical models of the three different architectures: the proposed perception-based distributed architecture, the conventional centralized architecture and perception-based centralized architecture have been constructed by using queuing theory to reflect the traffic generated, transmitted and processed at the perception-based distributed leaders, the perception-based centralized top leader, and the centralized server. The performance of these three different architectures has been considered in 4 different aspects. While the distributed architecture is better than the centralized architecture for a scalable multimedia conferencing service, it brings many problems to users who are using a wireless network to participate into the conferencing service. A special solution should be found out for mobile users in the next part of the thesis. Lastly, the distributed cross-layer scalable video conferencing services over the next generation convergent network is enabled. For that, an IMS-based distributed multimedia conferencing services for Next Generation Convergent Networks is proposed. [...]

1. Main Contributions made by the supplicant: This thesis proposes an Open Computing Language (OpenCL) framework to address the challenges of implementation of graph algorithms on parallel architectures and large scale graph processing. The proposed framework uses the front-end of the existing Falcon DSL compiler, andso, programmers enjoy conventional, imperative and shared memory programming style. The back-end of the framework generates implementations of graph algorithms in OpenCL to target single device architectures. The generated OpenCL code is portable across various platforms, e.g., CPU and GPU, and also vendors, e.g., NVIDIA, Intel and AMD. The framework automatically generates code for thread management and memory management for the devices. It hides all the lower level programming details from the programmers. A few optimizations are applied to reduce the execution time. The large graph processing challenge is tackled through graph partitioning over multiple devices of a single node and multiple nodes of a distributed cluster. The programmer codes a graph algorithm in Falcon assuming that the graph fits into single machine memory and the framework handles graph partitioning without any intervention by the programmer. The framework analyses the Abstract Syntax Tree (AST) generated by Falcon to find all the necessary information about communication and synchronization. It automatically generates code for message passing to hide the complexity of programming in a distributed environment. The framework also applies a set of optimizations to minimize the communication latency. The thesis reports results of several experiments conducted on widely used graph algorithms: single source shortest path, pagerank and minimum spanning tree to name a few. Experimental evaluations show that the reported results are comparable to the state-of-art non-portable graph DSLs and frameworks on a single node. Experiments in a distributed environment to show the scalability and efficiency of the framework are also described. 2. Summary of the Referees' Written Comments: Extracts from the referees' reports are provided below. A copy of the written replies to the clarifications sought by the external examiner is appended to this report. Referee 1: This thesis extends the Falcon framework with OpenCL for parallel graph processing on multi-device and multi-node architectures. The thesis makes important contributions. Processing large graphs in short time is very important, and making use of multiple nodes and devices is perhaps the only way to achieve this. Towards this, the thesis makes good contributions for easy programming, compiler transformations and efficient runtime systems. One of the commendable aspects of the thesis that it demonstrates with graphs that cannot be accommodated In the memory of a single device. The thesis is generally written well. The related work coverage is very good. The magnitude of thesis excellent for a Masters work. The experimental setup is very comprehensive with good set of graphs, good experimental comparisons with state-of-art works and good platforms. Particularly. the demonstration with a GPU cluster with multiple GPU nodes (Chapter 5) is excellent. The attempt to demonstrate scalability with 2, 4 and 8 nodes is also noteworthy. However, the contributions on optimizations are weak. Most of the optimizations and compiler transformations are straight-forward. There should be summary observations on the results in Chapter 3, especially given that the results are mixed and don't quite clearly convey the clear advantages of their work. The same is the case with multi-device results in chapter 4, where the results are once again mixed. Similarly, the speedups and scalability achieved with multiple nodes are not great. The problem size justification in the multi-node results is not clear. (Referee 1 also indicates a couple of minor changes to the thesis). Referee 2: The thesis uses the OpenCL framework to address the problem of programming graph algorithms on distributed systems. The use of OpenCL ensures that the generated code is platform-agnoistic and vendor-agnoistic. Sufficient experimentation with large scale graphs and reasonable size clusters have been conducted to demonstrate the scalability and portability of the code generated by the framework. The automatically generated code is almost as efficient as manually written code. The thesis is well written and is of high quality. The related work section is well organized and displays a good knowledge of the subject matter under consideration. The author has made important contributions to a good publication as well. 3. An Account of the Open Oral Examination: The oral examination of Ms. Parita Patel took place during 10 AM and 11AM on 27th November 2017, in the Seminar Hall of the Department of Computer Science and Automation. The members of the Oral Examination Board present were, Prof. Sathish Vadhiyar, external examiner and Prof. Y. N. Srikant, research supervisor. The candidate presented the work in an open defense seminar highlighting the problem domain, the methodology used, the investigations carried out by her, and the resulting contributions documented in the thesis before an audience consisting of the examiners, some faculty members, and students. Some of the questions posed by the examiners and the members of the audience during the oral examination are listed below. 1. How much is the overlap between Falcon work and this thesis? Response: We have used the Falcon front end in our work. Further, the existing Falcon compiler was useful to us to test our own implementation of algorithms in Falcon. 2. Why are speedup and scalability not very high with multiple nodes? Response: For the multi-node architecture, we were not able to achieve linear scalability because, with the increase in number of nodes, communication cost increases significantly. Unless the computation cost in the nodes is significant and is much more than the communication cost, this is bound to happen. 3. Do you have plans of making the code available for use by the community? Response: The code includes some part of Falcon implementation (front-end parsing/grammar) also. After discussion with the author of Falcon, the code can be made available to the community. 4. How can a graph that does not fit into a single device fit into a single node in the case of multiple nodes? Response: Single node machine used in the experiments of “multi-device architecture” contains multiple devices while each node used in experiments of “multi-node architecture” contains only a single device. So, the graph which does not fit into single-node-single-device memory can fit into single-node-multi-device after partitioning. 5. Is there a way to permit morph algorithms to be coded in your framework? Response: Currently, our framework does not translate morph algorithms. Supporting morph algorithms will require some kind of runtime system to manage memory on GPU since morph algorithms add and remove the vertices and edges to the graph dynamically. This can be further explored in future work. 6. Is it possible to accommodate FPGA devices in your framework? Response: Yes, we can support FPGA devices (or any other device that is compatible for OpenCL) just by specifying the device type in the command line argument. We did not work with other devices because CPU and GPU are generally used to process graph algorithms. The candidate provided satisfactory answers to all the questions posed and the clarifications sought by the audience and the examiners during the presentation. The candidate's overall performance during the open defense and the oral examination was very satisfactory to the oral examination board. 4. Certificate of Corrections and Changes: All the necessary corrections and changes suggested by the examiners have been made in the thesis and these have been verified by the members of the oral examination board. The thesis has been recommended for acceptance in its revised form. 5. Final Recommendation: In view of the recommendations of the referees and the satisfactory performance of the candidate in the oral examination, the oral examination board recommends that the thesis of Ms. ParitaPatel be accepted for the award of the M.Sc(Engg.) Degree of the Institute. Response to the comments by the external examiner on the M.Sc(Engg.) thesis “Compilation of Graph Algorithms for Hybrid, Cross-Platform, and Distributed Architectures” by Parita Patel 1. Comment: The contributions on optimizations are weak. Response: The novelty of this thesis is to make the Falcon platform agnostic, and additionally process large scale graphs on multi-devices of a single node and multi-node clusters seamlessly. Our framework performs similar to the existing frameworks, but at the same time, it targets several types of architectures which are not possible in the existing works. Advanced optimizations are beyond the scope of this thesis. 2. Comment: The translation of Falcon to OpenCL is simple. While the translation of Falcon to OpenCL was not hard, figuring out the details of the translation for multi-device and multi-node architectures was not simple. For example, design of implementations for collection, set, global variables, concurrency, etc., were non-trivial. These designs have already been explained in the appropriate places in the thesis. Further, such large software introduced its own intricacies during development. 3. Comment: Lines between Falcon work and this work are not clear. Response: Appendix-A shows the falcon implementation of all the algorithms which we used to run the experiments. We compiled these falcon implementations through our framework and subsequently ran the generated code on different types of target architectures and compared the results with other framework's generated code. These falcon programs were written by us. We have also used the front-end of the Falcon compiler and this has already been stated in the thesis (page 16). 4. Comment: There should be a summary of observations in chapter 3. Response: Summary of observations have been added to chapter 3 (pages 35-36), chapter 4 (page 46), and chapter 5 (page 51) of the thesis. 5. Comment: Speedup and scalability achieved with multiple nodes are not great. Response: For the multi-node architecture, we were not able to achieve linear scalability because, with the increase in number of nodes, communication cost increases significantly. Unless the computation cost in the nodes is significant and is much more than the communication cost, this is bound to happen. 6. Comment: It will be good to separate the related work coverage into a separate chapter. Response: The related work is coherent with the flow in chapter 1. It consists of just 4.5 pages and separating it into a separate chapter would make both (rest of) chapter 1 and the new chapter very small. Therefore, we do not recommend it. 7. Comment: The code should be made available for use by the community. Response: The code includes some part of Falcon code (front-end parsing/grammar) also. After discussion with the author of Falcon, the code can be made available to the community. 8. Comment: Page 28: Shouldn’t the else part be inside the kernel? Response: There was some missing text and a few minor changes in Figure 3.14 (page 28) which have been incorporated in the corrected thesis. 9. Comment: Figure 4.1 needs to be explained better. Response: Explanation for Figure 4.1 (pages 38-39) has been added to the thesis. 10. Comment: The problem size justification in the multi-node results is not clear. Response: Single node machine used in the experiments of “multi-device architecture” contains multiple devices while each node used in experiments of “multi-node architecture” contains only a single device. So, the graph which does not fit into single-node-single-device memory can fit into single-node-multi-device after partitioning. Name of the Candidate: Parita Patel (S.R. No. 04-04-00-10-21-14-1-11610) Degree Registered: M.Sc(Engg.) Department: Computer Science & Automation Title of the Thesis: Compilation of Graph Algorithms for Hybrid, Cross-Platform and Graph algorithms are abundantly used in various disciplines. These algorithms perform poorly due to random memory access and negligible spatial locality. In order to improve performance, parallelism exhibited by these algorithms can be exploited by leveraging modern high performance parallel computing resources. Implementing graph algorithms for these parallel architectures requires manual thread management and memory management which becomes tedious for a programmer. Large scale graphs cannot fit into the memory of a single machine. One solution is to partition the graph either on multiple devices of a single node or on multiple nodes of a distributed network. All the available frameworks for such architectures demand unconventional programming which is difficult and error prone. To address these challenges, we propose a framework for compilation of graph algorithms written in an intuitive graph domain-specific language, Falcon. The framework targets shared memory parallel architectures, computational accelerators and distributed architectures (CPU and GPU cluster). First, it analyses the abstract syntax tree (generated by Falcon) and gathers essential information. Subsequently, it generates optimized code in OpenCL for shared-memory parallel architectures and computational accelerators, and OpenCL coupled with MPI code for distributed architectures. Motivation behind generating OpenCL code is its platform-agnostic and vendor-agnostic behavior, i.e., it is portable to all kinds of devices. Our framework makes memory management, thread management, message passing, etc., transparent to the user. None of the available domain-specific languages, frameworks or parallel libraries handle portable implementations of graph algorithms. Experimental evaluations demonstrate that the generated code performs comparably to the state-of-the-art non-portable implementations and hand-tuned implementations. The results also show portability and scalability of our framework.

Made available in DSpace on 2016-06-02T19:05:59Z (GMT). No. of bitstreams: 1 4685.pdf: 5011854 bytes, checksum: 20592729fa201c69f10672347d91c2a5 (MD5) Previous issue date: 2012-08-31 / Financiadora de Estudos e Projetos / Managing multiple systems such as machine tools, vehicles, aircraft, among others, demand a very intense flow of data between them and the system manager. Researches have been developed in the design and implementation of scalable architectures that meet these demands leading to interesting questions of performance. The objective of this work is to propose a low cost scalable architecture for embedded applications, using pools of personal computers for high performance storage, retrieval and processing of information. It is driven by strong demand for tracking and monitoring of machines and vehicles, covering concepts of mobile networks with satellites and GPRS technology together with the requirement of reliability and performance in the sending of information. Proposes the definition of a server structure, whose distribution is transparent to the application, which is responsible for the receipt of messages from embedded devices via radio frequency technology, decoding and integration of information in the database and subsequent recovery of these information s. Through simulation of different modeled strategies using queuing theory to determine the architecture and the use of predictive mathematical methods for estimating the future burden for the server application, it was possible to obtain a solution that satisfactorily met the assumptions of the research. Thus, it is concluded that it is possible to estimate trends peaks processing information for telemetry applications fleet. / O gerenciamento remoto de múltiplos sistemas tais como máquinas operatrizes, veículos, aviões, dentre outros, demanda um fluxo bastante intenso de dados entre eles e o sistema gerenciador. Pesquisas têm sido desenvolvidas na concepção e implementação de arquiteturas escaláveis que atendam essas demandas levando a questões interessantes de desempenho. O objetivo deste trabalho é propor uma arquitetura escalável de baixo custo para aplicações embarcadas, utilizando pools de computadores pessoais para obter alto desempenho no armazenamento, recuperação e tratamento da informação. É motivado pela grande demanda de rastreamento e monitoramento de máquinas e veículos, contemplando conceitos de redes móveis com tecnologia de satélites e GPRS, juntamente com o requisito de confiabilidade e desempenho no envio da informação. Propõe a definição de uma estrutura de servidor, cuja distribuição é transparente para a aplicação, à qual compete o recebimento das mensagens dos equipamentos embarcados através de tecnologia de radio frequência, decodificação e inserção das informações num banco de dados e posterior recuperação destas informações. Através da simulação de diferentes estratégias modeladas, utilizando a teoria das filas, para determinação da arquitetura e a utilização de métodos matemáticos preditivos para estimação da carga futura para a aplicação servidora, foi possível obter uma solução que atendeu satisfatoriamente às premissas da pesquisa. Dessa forma, conclui-se que é possível estimar tendências de picos de processamento de informação para aplicações de telemetria de frotas.

Multi-parti de conférence multimédia est le type le plus compliqué de la communication mais aussi le service principalement utilisé sur Internet. Il est aussi la killer application sur les réseaux 4G. Dans cette recherche, nous nous concentrons sur trois parties principales du service de téléconférence: L'architecture de distribution de médias, le codage vidéo, ainsi que l'intégration du service dans les infrastructures sans fil 4G. Nous proposons un algorithme d'application nouvelle couche de multidiffusion utilisant une architecture de services distribués. L'algorithme proposé estime que les limites de la perception humaine, tout en participant à une conférence vidéo afin de minimiser le trafic qui n'est pas nécessaire pour la session de communication. Riche des modèles théoriques de la perception basée proposé architecture distribuée, l'architecture traditionnelle centralisée et basée sur la perception architecture centralisée ont été construits en utilisant la théorie d'attente afin de refléter le trafic généré, transmises et traitées à l'pairs distribués, les dirigeants et le serveur centralisé. La performance des architectures a été pris en compte dans les différents aspects de la durée totale d'attente, le retard de point à point et le taux de service requis pour le débit total. Ces résultats aident le lecteur à avoir une vue globale des performances de la proposition dans une comparaison équitable avec les méthodes conventionnelles. Pour construire l'arbre de distribution des médias pour l'architecture distribuée, une fonction de coût nouvelle application-aware multi-variable est proposée. Il tient compte des besoins variables des applications et des mises à jour dynamiquement les ressources disponibles nécessaires pour parvenir à un nœud particulier sur l'arbre de distribution de l'ALM. Codage vidéo scalable est utilisé comme le principal multi-couche codec à la conférence. Afin d'évaluer la performance de la fonction de coût multi-variable nouvellement proposées dans une application dynamique et avancé environnement réseau sans fil, codage vidéo scalable (SVC) des transmissions sur un réseau overlay ALM construite sur un réseau sous-4G/WiMAX réelles ont été utilisées. Nous avons développé EvalSVC et l'utiliser comme plate-forme principale pour évaluer la fonction de coût proposé. Comme un problème commun, l'architecture distribuée nécessite que les pairs contribuent une partie de leur bande passante et capacité de calcul afin de maintenir la superposition mutuelle inter-connexion. Cette exigence se développe en un grave problème pour les utilisateurs mobiles et l'infrastructure sans fil, comme la ressource radio de ce réseau est extrêmement coûteux, et est l'une des raisons pour lesquelles l'architecture distribuée n'a pas été largement appliquée dans la prochaine génération (4G) des réseaux. C'est aussi la raison principale pour laquelle les services multimédias tels que vidéo-conférence doivent s'appuyer sur une architecture centralisée coûteuse construite sur un des contrôleurs des médias coûteux fonction des ressources (CRFM), via l'IMS (IP Multimedia Subsystem). Ce travail de recherche propose une nouvelle architecture distribuée utilisant la capacité de renseignement et extra, actuellement disponibles sur le LTE et stations de base WiMAX de réduire le besoin des débits que chacun a à fournir par les pairs afin de maintenir le réseau overlay. Cette réduction permet d'économiser des ressources précieuses et de radio permet une architecture distribuée pour fournir des services de visioconférence sur les réseaux 4G, avec tous les avantages d'une architecture distribuée, comme la flexibilité, l'évolutivité, les petits retards et à moindre coût. De plus, cela peut être mis en œuvre avec une modification minimale de la plate-forme standardisée IMS et les infrastructures 4G, économisant ainsi les opérateurs et les fournisseurs de services d'investissements excessifs. [...] / Multimedia services are the killer applications on next generation convergent networks. Video contents are the most resource consuming part of a multimedia flux. Video transmission, video multicast and video conferencing services are the most popular types of video communication with increasing difficulty levels. Four main parts of the distributed cross-layer scalable multimedia services over next generation convergent networks are considered in this research work, both from the architecture and performance point of views. Firstly, we evaluate the performance of scalable multimedia transmissions over an overlay network. For that, we evaluate the performance of scalable video end-to-end transmissions over EvalSVC. It is capable of evaluating the end-to-end transmission of SVC bit-streams. The output results are both objective and subjective metrics of the video transmission. Through the interfaces with real networks and an overlay simulation platform, the transmission performance of different types of SVC scalability and AVC bit-streams on a bottle-neck and an overlay network will be evaluated. This evaluation is new because it is conducted on the end-to-end transmission of SVC contents and not on the coding performance. Next, we will study the multicast mechanism for multimedia content over an overlay network in the following part of this PhD thesis. Secondly, we tackle the problems of the distributed cross-layer scalable multimedia multicast over the next generation convergent networks. For that, we propose a new application-network cross layer multi-variable cost function for application layer multicast of multimedia delivery over convergent networks. It optimizes the variable requirements and available resources from both the application and the network layers. It can dynamically update the available resources required for reaching a particular node on the ALM's media distribution tree. Mathematical derivation and theoretical analysis have been provided for the newly proposed cost function so that it can be applied in more general cases of different contexts. An evaluation platform of an overlay network built over a convergent underlay network comprised of a simulated Internet topology and a real 4G mobile WiMAX IEEE802.16e wireless network is constructed. If multicast is the one-to-many mechanism to distribute the multimedia content, a deeper study on the many-to-many mechanism will be done in the next part of the thesis through a new architecture for video conferencing services. Thirdly, we study the distributed cross-layer scalable video conferencing services over the overlay network. For that, an enriched human perception-based distributed architecture for scalable video conferencing services is proposed with theoretical models and performance analysis. Rich theoretical models of the three different architectures: the proposed perception-based distributed architecture, the conventional centralized architecture and perception-based centralized architecture have been constructed by using queuing theory to reflect the traffic generated, transmitted and processed at the perception-based distributed leaders, the perception-based centralized top leader, and the centralized server. The performance of these three different architectures has been considered in 4 different aspects. While the distributed architecture is better than the centralized architecture for a scalable multimedia conferencing service, it brings many problems to users who are using a wireless network to participate into the conferencing service. A special solution should be found out for mobile users in the next part of the thesis. Lastly, the distributed cross-layer scalable video conferencing services over the next generation convergent network is enabled. For that, an IMS-based distributed multimedia conferencing services for Next Generation Convergent Networks is proposed. [...]

La gestió de xarxes és un camp molt ampli i inclou molts aspectes diferents. Aquesta tesi doctoral està centrada en la gestió dels recursos en les xarxes de banda ampla que disposin de mecanismes per fer reserves de recursos, com per exemple Asynchronous Transfer Mode (ATM) o Multi-Protocol Label Switching (MPLS). Es poden establir xarxes lògiques utilitzant els Virtual Paths (VP) d'ATM o els Label Switched Paths (LSP) de MPLS, als que anomenem genèricament camins lògics. Els usuaris de la xarxa utilitzen doncs aquests camins lògics, que poden tenir recursos assignats, per establir les seves comunicacions. A més, els camins lògics són molt flexibles i les seves característiques es poden canviar dinàmicament. Aquest treball, se centra, en particular, en la gestió dinàmica d'aquesta xarxa lògica per tal de maximitzar-ne el rendiment i adaptar-la a les connexions ofertes.En aquest escenari, hi ha diversos mecanismes que poden afectar i modificar les característiques dels camins lògics (ample de banda, ruta, etc.). Aquests mecanismes inclouen els de balanceig de la càrrega (reassignació d'ample de banda i reencaminament) i els de restauració de fallades (ús de camins lògics de backup). Aquests dos mecanismes poden modificar la xarxa lògica i gestionar els recursos (ample de banda) dels enllaços físics. Per tant, existeix la necessitat de coordinar aquests mecanismes per evitar possibles interferències. La gestió de recursos convencional que fa ús de la xarxa lògica, recalcula periòdicament (per exemple cada hora o cada dia) tota la xarxa lògica d'una forma centralitzada. Això introdueix el problema que els reajustaments de la xarxa lògica no es realitzen en el moment en què realment hi ha problemes. D'altra banda també introdueix la necessitat de mantenir una visió centralitzada de tota la xarxa. En aquesta tesi, es proposa una arquitectura distribuïda basada en un sistema multi agent. L'objectiu principal d'aquesta arquitectura és realitzar de forma conjunta i coordinada la gestió de recursos a nivell de xarxa lògica, integrant els mecanismes de reajustament d'ample de banda amb els mecanismes de restauració preplanejada, inclosa la gestió de l'ample de banda reservada per a la restauració. Es proposa que aquesta gestió es porti a terme d'una forma contínua, no periòdica, actuant quan es detecta el problema (quan un camí lògic està congestionat, o sigui, quan està rebutjant peticions de connexió dels usuaris perquè està saturat) i d'una forma completament distribuïda, o sigui, sense mantenir una visió global de la xarxa. Així doncs, l'arquitectura proposada realitza petits rearranjaments a la xarxa lògica adaptant-la d'una forma contínua a la demanda dels usuaris. L'arquitectura proposada també té en consideració altres objectius com l'escalabilitat, la modularitat, la robustesa, la flexibilitat i la simplicitat.El sistema multi agent proposat està estructurat en dues capes d'agents: els agents de monitorització (M) i els de rendiment (P). Aquests agents estan situats en els diferents nodes de la xarxa: hi ha un agent P i diversos agents M a cada node; aquests últims subordinats als P. Per tant l'arquitectura proposada es pot veure com una jerarquia d'agents. Cada agent és responsable de monitoritzar i controlar els recursos als que està assignat. S'han realitzat diferents experiments utilitzant un simulador distribuït a nivell de connexió proposat per nosaltres mateixos. Els resultats mostren que l'arquitectura proposada és capaç de realitzar les tasques assignades de detecció de la congestió, reassignació dinàmica d'ample de banda i reencaminament d'una forma coordinada amb els mecanismes de restauració preplanejada i gestió de l'ample de banda reservat per la restauració. L'arquitectura distribuïda ofereix una escalabilitat i robustesa acceptables gràcies a la seva flexibilitat i modularitat. / Network management is a wide field including many different topics. This thesis focuses on resource management of broadband networks that have the mechanisms for performing resource reservation, such as Asynchronous Transfer Mode (ATM) or Multi-Protocol Label Switching (MPLS). Logical networks can be established by using Virtual Paths (VP) in ATM or Label Switched Paths (LSP) in MPLS, which we call generically Logical Paths (LP). The network users then use these LPs, which can have pre-reserved resources, to establish their communications. Moreover, LPs are very flexible and their characteristics can be dynamically changed. This work focuses, in particular, on the dynamic management of these logical paths in order to maximise the network performance by adapting the logical network to the offered connections.In this scenario, there are several mechanisms that can affect and modify certain features of the LPs (bandwidth, route, etc.). They include load balancing mechanisms (bandwidth reallocation and re-routing) and fault restoration (utilisation of backup LPs). These two mechanisms can modify the logical network and manage the resources (bandwidth) of the physical links. Therefore, due to possible interferences, there is a need to co-ordinate these mechanisms. Conventional resource management, using a logical network, performs a centralised recalculation of the whole logical network periodically (e.g. every hour / day). This brings the problem that the logical network readjustments do not happen when a problem occurs. Moreover, there is a need of maintaining a centralised network overview. In this thesis, a distributed architecture, based on a Multi-Agent System (MAS), is proposed. The main objective of this architecture is to perform joint resource management at a logical network level, integrating the bandwidth reallocation and LP re-routing with pre-planned restoration and spare bandwidth management. This is performed continuously, not periodically, when a problem is detected (an LP is congested, i.e. it is rejecting new user connections because it is already saturated with user connections) in a completely distributed way, i.e. without any central network overview. Therefore, the proposed architecture performs small rearrangements in the logical network and thus it is continuously being adapted to the user demands. The proposed architecture also considers other objectives, such as scalability, modularity, robustness, simplicity and flexibility. The proposed MAS is structured in two layers of agents: The network Monitoring (M) agents and the Performance (P) agents. All these agents are situated at different network nodes, where the computing facilities are. There is one P agent and several M agents on every node. The M agents are subordinated to the P agents, therefore the proposed architecture can be seen as a hierarchy of agents. Each agent is responsible for monitoring and controlling the resources they are assigned to. We have performed several experiments, using a connection level distributed simulator of our own design. The results show that our architecture is capable of performing the assigned tasks of detecting congestion, dynamic bandwidth reallocation and re-routing in a co-ordinated way with the pre-planned restoration and the spare capacity management. The distributed architecture offers a suitable scalability and robustness due to its flexibility and modularity.

Cette thèse s'intéresse à la modélisation et à l'analyse dessystèmes temps-réel distribués.Un système distribué est constitué de plusieurs composantsqui évoluent de manière partiellement indépendante. Lorsque des actionsexécutables par différentscomposants sont indépendantes, elles sont dites concurrentes.Dans ce cas, elles peuvent être exécutées dans n'importe quel ordre, sanss'influencer, et l'état atteint après ces actions ne dépend pas de leur ordred'exécution.Dans les systèmes temps-réel distribués, les contraintes de temps créent desdépendances complexes entre les composants et les événements qui ont lieu surces composants. Malgré l'omniprésence et l'aspect critique de ces systèmes,beaucoup de leurs propriétés restent encore à étudier.En particulier, la nature distribuée de ces systèmes est souvent laissée de côté.Notre travail s'appuie sur deux formalismesde modélisation: les réseaux de Petri temporels et les réseaux d'automatestemporisés, et est divisé en deux parties.Dans la première partie, nous mettons en évidence les différences entre lessystèmes temporisés centralisés et les systèmes temporisés distribués. Nouscomparons les formalismes principaux et leurs extensions, avec une approcheoriginale qui considère la concurrence.En particulier, nous montrons comment transformer un réseau de Petri temporelen un réseau d'automates temporisés qui a le même comportement distribué.Nous nous intéressons ensuite aux horloges partagées dans lesréseaux d'automates temporisés. Les horloges partagées sont problématiqueslorsque l'on envisage d'implanter ces modèles sur des architecturesdistribuées. Nous montrons comment se passer des horloges partagées, touten préservant le comportement distribué, lorsque cela est possible.Dans la seconde partie, nous nous attachons à formaliser les dépendancesentre les événements dans les représentations en ordre partieldes exécutions des réseaux de Petri (temporels ou non).Les réseaux d'occurrence sont une de ces représentations, et leur structuredonne directement les relations de causalité, conflit et concurrence entreles événements. Cependant, nous montrons que, même dans le cas non temporisé,certaines relations logiques entre les événements nepeuvent pas être directement décrites par ces relations structurelles.Après avoir formalisé les relations logiques en question, nous résolvons leproblème de synthèse suivant: étant donnée une formule logique qui décrit unensemble d'exécutions, construire un réseau d'occurrence associé,quand celui-ci existe.Nous étudions ensuite les relations logiques dans un cadre temporisé simplifié,et montrons que le temps crée des dépendances complexes entre les événements.Ces dépendances peuvent être utilisées pour définir des dépliages canoniques deréseaux de Petri temporels, dans ce cadre simplifié. / This thesis is concerned with the modeling and the analysis of distributedreal-time systems. In distributed systems, components evolve partlyindependently: concurrent actions may be performed in any order, withoutinfluencing each other and the state reached after these actions does notdepends on the order of execution. The time constraints in distributed real-timesystems create complex dependencies between the components and the events thatoccur. So far, distributed real-time systems have not been deeply studied, andin particular the distributed aspect of these systems is often left aside. Thisthesis explores distributed real-time systems. Our work on distributed real-timesystems is based on two formalisms: time Petri nets and networks of timedautomata, and is divided into two parts.In the first part, we highlight the differences between centralized anddistributed timed systems. We compare the main formalisms and their extensions,with a novel approach that focuses on the preservation of concurrency. Inparticular, we show how to translate a time Petri net into a network of timedautomata with the same distributed behavior. We then study a concurrency relatedproblem: shared clocks in networks of timed automata can be problematic when oneconsiders the implementation of a model on a multi-core architecture. We showhow to avoid shared clocks while preserving the distributed behavior, when thisis possible.In the second part, we focus on formalizing the dependencies between events inpartial order representations of the executions of Petri nets and time Petrinets. Occurrence nets is one of these partial order representations, and theirstructure directly provides the causality, conflict and concurrency relationsbetween events. However, we show that, even in the untimed case, some logicaldependencies between event occurrences are not directly described by thesestructural relations. After having formalized these logical dependencies, wesolve the following synthesis problem: from a formula that describes a set ofruns, we build an associated occurrence net. Then we study the logicalrelations in a simplified timed setting and show that time creates complexdependencies between event occurrences. These dependencies can be used to definea canonical unfolding, for this particular timed setting.