With the advent of Network Function Virtualization (NFV), network services that traditionally run on proprietary dedicated hardware can now be realized using Virtual Network Functions (VNFs) that are hosted on general-purpose commodity hardware. This new network paradigm offers a great flexibility to Internet service providers (ISPs) for efficiently operating their networks (collecting network statistics, enforcing management policies, etc.). However, introducing NFV requires an investment to deploy VNFs at certain network nodes (called VNF-nodes), which has to account for practical constraints such as the deployment budget and the VNF-node limited resources. While gradually transitioning to NFV, ISPs face the problem of where to efficiently introduce NFV; here, we measure the efficiency by the amount of traffic that can be served in an NFV-enabled network. This problem is non-trivial as it is composed of two challenging subproblems: 1) placement of VNF-nodes; 2) allocation of the VNF-nodes' resources to network flows. These two subproblems must be jointly considered to satisfy the objective of serving the maximum amount of traffic. We first consider this problem for the one-dimensional setting, where all network flows require one network function, which requires a unit of resource to process a unit of flow. In contrast to most prior work that often neglects either the budget constraint or the resource allocation constraint, we explicitly consider both of them and prove that accounting for them introduces several new challenges. Specifically, we prove that the studied problem is not only NP-hard but also non-submodular. To address these challenges, we introduce a novel relaxation method such that the objective function of the relaxed placement subproblem becomes submodular. Leveraging this useful submodular property, we propose two algorithms that achieve an approximation ratio of $\frac{1}{2}(1-1/e)$ and $\frac{1}{3}(1-1/e)$ for the original non-relaxed problem, respectively. Next, we consider the multi-dimensional setting, where flows can require multiple network functions, which can also require a different amount of each resource to process a unit of flow. To address the new challenges arising from the multi-dimensional setting, we propose a novel two-level relaxation method that allows us to draw a connection to the sequence submodular theory and utilize the property of sequence submodularity along with the primal-dual technique to design two approximation algorithms. Finally, we perform extensive trace-driven simulations to show the effectiveness of the proposed algorithms. While the NFV paradigm offers great flexibility to network operators for efficient management of their networks, VNF instances are typically more prone to error and more vulnerable to security threats compared with dedicated hardware devices. Therefore, the NFV paradigm also poses new challenges concerning failure resilience. That has motivated us to consider robustness with respect to the class of sequence submodular function maximization problem, which has a wide range of applications, including those in the NFV domain. Submodularity is an important property of set functions and has been extensively studied in the literature. It models set functions that exhibit a diminishing returns property, where the marginal value of adding an element to a set decreases as the set expands. This notion has been generalized to considering sequence functions, where the order of adding elements plays a crucial role and determines the function value; the generalized notion is called sequence (or string) submodularity. In this part of the dissertation, we study a new problem of robust sequence submodular maximization with cardinality constraints. The robustness is against the removal of a subset of elements in the selected sequence (e.g., due to malfunctions or adversarial attacks). Compared to robust submodular maximization for set function, new challenges arise when sequence functions are concerned. Specifically, there are multiple definitions of submodularity for sequence functions, which exhibit subtle yet critical differences. Another challenge comes from two directions of monotonicity: forward monotonicity and backward monotonicity, both of which are important to proving performance guarantees. To address these unique challenges, we design two robust greedy algorithms: while one algorithm achieves a constant approximation ratio but is robust only against the removal of a subset of contiguous elements, the other is robust against the removal of an arbitrary subset of the selected elements but requires a stronger assumption and achieves an approximation ratio that depends on the number of the removed elements. Finally, we consider important problems that arise in the production networks, where packets need to pass through an ordered set of network functions called Service Function Chains (SFC) before reaching the destination. We study the following problems: (1) How to find an SFC-constrained shortest path between any pair of nodes? (2) What is the achievable SFC-constrained maximum flow? We propose a transformation of the network graph to minimize the computational complexity of subsequent applications of any shortest path algorithm. Moreover, we formulate the SFC-constrained maximum flow problem as a fractional multicommodity flow problem and develop a combinatorial algorithm for a special case of practical interest. / Computer and Information Science

Avec la croissance exponentielle des demandes de service, les opérateurs ont déployé de nombreux équipements, et par conséquent, la gestion du réseau est devenue de plus en plus difficile et coûteuse. La virtualisation des fonctions réseau (NFV) a été proposée comme un nouveau paradigme pour réduire les coûts liés à l’acquisition et à la maintenance pour les réseaux de télécommunications. Dans ce travail de thèse, nous nous intéressons aux problèmes du chaînage des fonctions virtuelles (VNFs) qui combinent des décisions de localisation des VNFs et de routage des demandes. D'un point de vue d'optimisation, ce problème est une combinaison des problèmes de localisation (pour la partie d'installation des VNFs) et de conception de réseaux (pour la partie de routage). Ces deux problèmes ont été largement étudié dans la littérature. Cependant, leur combinaison représente des divers challenges en termes de modélisation et de résolution. Dans la première partie de cette thèse, nous considérons une version réaliste du problème du chaînage des VNFs (VNF-PR) afin de comprendre l'impact des différents aspects sur les coûts et les performances de gestion du réseau. Dans ce but, nous étendons le travail dans~\cite{Addis2015} en considérant des caractéristiques et des contraintes plus réalistes des infrastructures NFV et nous proposons un modèle de programmation linéaire et une heuristique mathématique pour le résoudre. Dans le but de mieux comprendre la structure du problème et ses propriétés, la deuxième partie de la thèse est orientée vers l'étude théorique du problème, où nous avons étudié une version compacte du problème du chaînage des VNFs. Nous fournissons des résultats sur la complexité de calcul sous divers cas de topologie et de capacité. Ensuite, nous proposons deux modèles et nous les testons sur un testbed avec plus de 100 instances différentes avec différents cas de capacité. Au final, nous abordons la scalabilité du problème en proposant des méthodes constructives et des méthodes heuristiques basées sur la programmation linéaire entière pour traiter efficacement des instances de taille grande (jusqu'à 60 nœuds et 1800 demandes). Nous montrons que les heuristiques proposées sont capables de résoudre efficacement des instances de taille moyenne (avec jusqu'à 30 nœuds et 1 000 demandes) de cas de capacité difficiles et de trouver de bonnes solutions pour les instances dures, où le modèle ne peut fournir aucune solution avec un temps de calcul limité. / Due to the exponential growth of service demands, telecommunication networks are populated with a large and increasing variety of proprietary hardware appliances, and this leads to an increase in the cost and the complexity of the network management. To overcome this issue, the NFV paradigm is proposed, which allows dynamically allocating the Virtual Network Functions (VNFs) and therefore obtaining flexible network services provision, thus reducing the capital and operating costs. In this thesis, we focus on the VNF Placement and Routing (VNF-PR) problem, which aims to find the location of the VNFs to allocate optimally resources to serve the demands. From an optimization point of view, the problem can be modeled as the combination of a facility location problem (for the VNF location and server dimensioning) and a network design problem (for the demands routing). Both problems are widely studied in the literature, but their combination represents, to the best of our knowledge, a new challenge. We start working on a realistic VNF-PR problem to understand the impact of different policies on the overall network management cost and performance. To this end, we extend the work in [1] by considering more realistic features and constraints of NFV infrastructures and we propose a linear programming model and a math-heuristic to solve it. In order to better understand the problem structure and its properties, in the second part of our work, we focus on the theoretical study of the problem by extracting a simplified, yet significant variant. We provide results on the computational complexity under different graph topology and capacity cases. Then, we propose two mathematical programming formulations and we test them on a common testbed with more than 100 different test instances under different capacity settings. Finally, we address the scalability issue by proposing ILP-based constructive methods and heuristics to efficiently deal with large size instances (with up to 60 nodes and 1800 demands). We show that our proposed heuristics can efficiently solve medium size instances (with up to 30 nodes and 1000 demands) of challenging capacity cases and provide feasible solutions for large size instances of the most difficult capacity cases, for which the models cannot find any solution even with a significant computational time.

O paradigma Network Function Virtualization (NFV) promete tornar as redes de computadores mais escaláveis e flexíveis, através do desacoplamento das funções de rede de hardware dedicado e fornecedor específico. No entanto, funções de rede computacionalmente intensivas podem ser difíceis de virtualizar sem degradação de desempenho. Neste contexto, Field-Programmable Gate Arrays (FPGAs) têm se mostrado uma boa opção para aceleração por hardware de funções de rede virtuais que requerem alta vazão, sem se desviar do conceito de uma infraestrutura NFV que visa alta flexibilidade. A avaliação de expressões regulares é um mecanismo importante e computacionalmente intensivo, usado para realizar Deep Packet Inpection, que pode ser acelerado por FPGA para atender aos requisitos de desempenho. Esta solução, no entanto, apresenta novos desafios em relação aos requisitos de confiabilidade. Particularmente para FPGAs baseados em SRAM, soft errors na memória de configuração são uma ameaça de confiabilidade significativa. Neste trabalho, apresentamos um mecanismo de tolerância a falhas abrangente para lidar com falhas de configuração na funcionalidade de módulos de avaliação de expressões regulares baseados em FPGA. Além disso, é introduzido um mecanismo de correção de erros que considera o posicionamento desses módulos no FPGA para reduzir o tempo de reparo do sistema, melhorando a confiabilidade e a disponibilidade. Os resultados experimentais mostram que a taxa de falha geral e o tempo de reparo do sistema podem ser reduzidos em 95% e 90%, respectivamente, com custos de área e performance admissíveis. / The Network Function Virtualization (NFV) paradigm promises to make computer networks more scalable and flexible by decoupling the network functions (NFs) from dedicated and vendor-specific hardware. However, network and compute intensive NFs may be difficult to virtualize without performance degradation. In this context, Field-Programmable Gate Arrays (FPGAs) have been shown to be a good option for hardware acceleration of virtual NFs that require high throughput, without deviating from the concept of an NFV infrastructure which aims at high flexibility. Regular expression matching is an important and compute intensive mechanism used to perform Deep Packet Inspection, which can be FPGA-accelerated to meet performance constraints. This solution, however, introduces new challenges regarding dependability requirements. Particularly for SRAM-based FPGAs, soft errors on the configuration memory are a significant dependability threat. In this work we present a comprehensive fault tolerance mechanism to deal with configuration faults on the functionality of FPGA-based regular expression matching engines. Moreover, a placement-aware scrubbing mechanism is introduced to reduce the system repair time, improving the system reliability and availability. Experimental results show that the overall failure rate and the system mean time to repair can be reduced in 95% and 90%, respectively, with manageable area and performance costs.

O paradigma Network Function Virtualization (NFV) promete tornar as redes de computadores mais escaláveis e flexíveis, através do desacoplamento das funções de rede de hardware dedicado e fornecedor específico. No entanto, funções de rede computacionalmente intensivas podem ser difíceis de virtualizar sem degradação de desempenho. Neste contexto, Field-Programmable Gate Arrays (FPGAs) têm se mostrado uma boa opção para aceleração por hardware de funções de rede virtuais que requerem alta vazão, sem se desviar do conceito de uma infraestrutura NFV que visa alta flexibilidade. A avaliação de expressões regulares é um mecanismo importante e computacionalmente intensivo, usado para realizar Deep Packet Inpection, que pode ser acelerado por FPGA para atender aos requisitos de desempenho. Esta solução, no entanto, apresenta novos desafios em relação aos requisitos de confiabilidade. Particularmente para FPGAs baseados em SRAM, soft errors na memória de configuração são uma ameaça de confiabilidade significativa. Neste trabalho, apresentamos um mecanismo de tolerância a falhas abrangente para lidar com falhas de configuração na funcionalidade de módulos de avaliação de expressões regulares baseados em FPGA. Além disso, é introduzido um mecanismo de correção de erros que considera o posicionamento desses módulos no FPGA para reduzir o tempo de reparo do sistema, melhorando a confiabilidade e a disponibilidade. Os resultados experimentais mostram que a taxa de falha geral e o tempo de reparo do sistema podem ser reduzidos em 95% e 90%, respectivamente, com custos de área e performance admissíveis. / The Network Function Virtualization (NFV) paradigm promises to make computer networks more scalable and flexible by decoupling the network functions (NFs) from dedicated and vendor-specific hardware. However, network and compute intensive NFs may be difficult to virtualize without performance degradation. In this context, Field-Programmable Gate Arrays (FPGAs) have been shown to be a good option for hardware acceleration of virtual NFs that require high throughput, without deviating from the concept of an NFV infrastructure which aims at high flexibility. Regular expression matching is an important and compute intensive mechanism used to perform Deep Packet Inspection, which can be FPGA-accelerated to meet performance constraints. This solution, however, introduces new challenges regarding dependability requirements. Particularly for SRAM-based FPGAs, soft errors on the configuration memory are a significant dependability threat. In this work we present a comprehensive fault tolerance mechanism to deal with configuration faults on the functionality of FPGA-based regular expression matching engines. Moreover, a placement-aware scrubbing mechanism is introduced to reduce the system repair time, improving the system reliability and availability. Experimental results show that the overall failure rate and the system mean time to repair can be reduced in 95% and 90%, respectively, with manageable area and performance costs.

O paradigma Network Function Virtualization (NFV) promete tornar as redes de computadores mais escaláveis e flexíveis, através do desacoplamento das funções de rede de hardware dedicado e fornecedor específico. No entanto, funções de rede computacionalmente intensivas podem ser difíceis de virtualizar sem degradação de desempenho. Neste contexto, Field-Programmable Gate Arrays (FPGAs) têm se mostrado uma boa opção para aceleração por hardware de funções de rede virtuais que requerem alta vazão, sem se desviar do conceito de uma infraestrutura NFV que visa alta flexibilidade. A avaliação de expressões regulares é um mecanismo importante e computacionalmente intensivo, usado para realizar Deep Packet Inpection, que pode ser acelerado por FPGA para atender aos requisitos de desempenho. Esta solução, no entanto, apresenta novos desafios em relação aos requisitos de confiabilidade. Particularmente para FPGAs baseados em SRAM, soft errors na memória de configuração são uma ameaça de confiabilidade significativa. Neste trabalho, apresentamos um mecanismo de tolerância a falhas abrangente para lidar com falhas de configuração na funcionalidade de módulos de avaliação de expressões regulares baseados em FPGA. Além disso, é introduzido um mecanismo de correção de erros que considera o posicionamento desses módulos no FPGA para reduzir o tempo de reparo do sistema, melhorando a confiabilidade e a disponibilidade. Os resultados experimentais mostram que a taxa de falha geral e o tempo de reparo do sistema podem ser reduzidos em 95% e 90%, respectivamente, com custos de área e performance admissíveis. / The Network Function Virtualization (NFV) paradigm promises to make computer networks more scalable and flexible by decoupling the network functions (NFs) from dedicated and vendor-specific hardware. However, network and compute intensive NFs may be difficult to virtualize without performance degradation. In this context, Field-Programmable Gate Arrays (FPGAs) have been shown to be a good option for hardware acceleration of virtual NFs that require high throughput, without deviating from the concept of an NFV infrastructure which aims at high flexibility. Regular expression matching is an important and compute intensive mechanism used to perform Deep Packet Inspection, which can be FPGA-accelerated to meet performance constraints. This solution, however, introduces new challenges regarding dependability requirements. Particularly for SRAM-based FPGAs, soft errors on the configuration memory are a significant dependability threat. In this work we present a comprehensive fault tolerance mechanism to deal with configuration faults on the functionality of FPGA-based regular expression matching engines. Moreover, a placement-aware scrubbing mechanism is introduced to reduce the system repair time, improving the system reliability and availability. Experimental results show that the overall failure rate and the system mean time to repair can be reduced in 95% and 90%, respectively, with manageable area and performance costs.

Les prestataires de service réseau doivent faire face à la demande croissante des besoins des utilisateurs, en particulier vers une plus grande flexibilité et toujours plus de capacité. La "softwerisation" et la "cloudification" des composants du réseau offrent une solution prometteuse pour obtenir l'agilité nécessaire afin de répondre dynamiquement à l'exigence au niveau de la consommation des ressources. Cette vision se traduit par le déploiement de la Virtualisation des Fonctions Réseau (NFV) où les Fonctions de Réseau Virtuels (VNFs) peuvent être associées pour créer des services réseau. Cette thèse étudie la problématique de l'allocation de ressources dans un système NFV afin de minimiser son coût sous contraintes sur l'interconnectivité entre les VNF, les ressources du système et les exigences de service. La principale considération est la réduction du coût global du déploiement en ressources informatiques. Nous étudions également d'autres objectifs à satisfaire tels que la migration des fonctions réseau et la gestion de la congestion. Notre premier objectif est d'augmenter notre compréhension de la performance d'un système NFV en étudiant le placement et le routage des fonctions réseau. Nous formalisons le problème dans une approche globale en tenant compte d'un large ensemble de paramètres pertinents. Nous prendrons en compte les cas statiques (Hors Ligne) et dynamiques (En Ligne) du problème. Nous proposons et analysons trois algorithmes heuristiques: deux sont conçus pour traiter de grandes dimensions du scenario "Hors Ligne" et le dernier est conçu pour résoudre le scénario "En Ligne". Les résultats montrent que notre solution surpasse l'état de l'art par rapport à l'indicateur de performance critique. Nous évaluons également l'impact de la migration d'une série de demandes simultanées et proposons une technique de migration simple pour ce système dynamique. A la lumière de ces premiers résultats, nous étendons notre étude afin d'améliorer l'efficacité de notre solution en proposant un modèle plus simple. La seconde partie de notre étude se concentre sur l'optimisation de l'utilisation des ressources d'un système NFV. La principale distinction est que nous pouvons appliquer le modèle à un système dynamique avec de grandes instances. De plus, nous fournissons également une méthode originale pour engendrer de fortes inégalités afin d'améliorer la résolution de la programmation linéaire (LP) dans un espace de dimension supérieur. Les résultats obtenus n'améliorent pas seulement le modèle, mais promettent aussi de pouvoir être utiliser efficacement dans d'autres modèles. Une troisième contribution de notre travail concerne le problème de routage dans NFV. En effet, une évolution importante des besoins des utilisateurs est représentée par la demande d'accès croissante aux ressources réseau, de stockage et de calcul afin de combiner dynamiquement le niveau de consommation de ressources avec leurs besoins de service. Par conséquent, nous nous intéressons au routage efficace d'une demande utilisateur à travers les noeuds qui traitent les fonctions impliquées dans une chaîne de services donnée. Nous proposons une formulation originale de ce problème basée sur la construction d'un réseau étendu. Nous formulons une solution mathématique exacte et proposons plusieurs algorithmes approximatifs tenant compte les principaux paramètres du système. Nous conclurons en soulignant les contributions principales de notre travail et proposons quelques pistes pour des travaux futurs. / Network service providers have to cope with the growing on-demand need from end-users as well as the diversity of usage. The "softwerization" and "loudification" of the network components offer a promising solution to achieve the agility necessary to dynamically match the servcice requirements with the level of resource consumption. Cloud-based solutions promises an economy of scale and simpler management. Virtualizing the many network appliances offers the flexibility to adapt to the varying service demand. This materializes with the deployment of Network Functions Virtualization (NFV) where Virtual Network Functions (VNFs) may be chained together to create network services. This dissertation studies the resource allocation problem in an NFV system for minimizing its cost under constraints on interconnectivity among VNFs, system resources, and service requirements. The main consideration is the reduction of the overall deployment cost while efficiently utilizing the available resources. In addition, a number of other important constraints are considered such as migration and congestion. Our first goal is to increase our understanding of the performance of an NFV system with respect to network functions placement and routing. We formalize the problem in a comprehensive maner taking into account a broad set of relevant parameters. The static (OFFLINE) and dynamic (ONLINE) cases are considered. We propose and analyze three heuristic algorithms: two for handling large dimensions of the OFFLINE problem and one designed to address the ONLINE scenario. The results show that our solution outperforms the state of the art with respect to critical performance index. We also evaluate the impact of migrating a set of running demands, and propose a simple migration technique for the dynamic system. We extend this work by proposing a simpler model to improve the performance of our solution. The second part of our work focuses on minimizing the resource utilization of an NFV system. The main distinctive point is that we can apply the model to a dynamic system with large instances. Moreover, we also provide an interesting method for generating some strong inequalities to improve the Linear Programming (LP) solving in a higher dimensional space. The obtained results are not only making the model easier but also can be used efficiently in other models. A third contribution focuses specifically on the routing problem in NFV. An important evolution of the users’ needs is represented by the dynamic on-demand access to network, vstorage and compute resources. Therefore, routing efficiently a demand across nodes handling the functions involved in a given service chain constitutes the a novel problem that we address in this last section. We provide an original formulation of this problem based on the construction of an expanded network. We derive the exact mathematical formulation and propose several approximate algorithms taking into account the main system’s parameters. We conclude by deriving some interesting insights both about the algorithms and the network performance. We finally conclude with our main findings and highlight many avenues for future work.

The advent of 5th generation of mobile networks (5G) will introduce some new challenges for the transport network. Different strategies can be employed by the network providers to address these challenges with the aim to achieve an efficient utilization of network resources. The most feasible option to achieve this goal is to introduce intelligence in the transport infrastructure by designing a flexible and programmable transport network. Network function virtualization (NFV) and dynamic resource sharing (DRS) are two possible techniques for realizing a flexible transport network. NFV allows to dynamically push network functions to different locations in the network, while DRS allows for sharing transport resources in a flexible manner. Both of these strategies can be realized by employing a programmable control framework based on software defined networking (SDN), which has implications on both the network data and control planes. However, this thesis specifically focuses on the data plane aspects of NFV and the control plane aspects of DRS. Considering the network caching as a specific example of network function, the data plane aspects of NFV are studied in terms of different architectural options for cache placement in order to see which options are the most efficient in terms of network power consumption and cost. The results presented in this thesis show that placing large-sized caches farther in the network for a large group of users is the most efficient approach. The control plane aspects of DRS are analyzed in terms of which provisioning strategy should be used for sharing a limited amount of transport resources. The analysis is presented for both a single-tenant case (i.e., where the role of service and network provider is played by the same entity), and a multi-tenant case (i.e., where a network provider manages the resources assigned to different service providers in an intelligent way). The results show that DRS performs much better than the conventional static approach (i.e., without sharing of resources), which translates into significant cost savings for the network providers. / <p>QC 20161115</p>

No description available.

Virtualization on top of high-performance servers has enabled the virtualization of network functions like caching, deep packet inspection, etc. Such Network Function Virtualization (NFV) is used to dynamically adapt to changes in network traffic and application popularity. We demonstrate how the combination of Software Defined Networking (SDN) and NFV can support the parallel operation of different Internet architectures on top of the same physical hardware. We introduce our architecture for this approach in an actual test setup, using CloudLab resources. We start of our evaluation in a small setup where we evaluate the feasibility of the SDN and NFV architecture and incrementally increase the complexity of the setup to run a live video streaming application. We use two vastly different protocol stacks, namely TCP/IP and NDN to demonstrate the capability of our approach. The evaluation of our approach shows that it introduces a new level of flexibility when it comes to operation of different Internet architectures on top of the same physical network and with this flexibility provides the ability to switch between the two protocol stacks depending on the application.

L'émergence de la technologie de virtualisation des fonctions réseau (NFV) a suscité un vif intérêt autour de la conception, la gestion et le déploiement de services réseau de manière flexible, automatisée et indépendante du fournisseur. La mise en œuvre de la technologie NFV devrait être une solution profitable pour les fournisseurs de services et les clients. Cependant, ce changement de paradigme, amorcé par NFV, nécessite un abandon progressif des services réseau fournis à travers des équipements dédiés. En contrepartie, un environnement totalement ou partiellement virtualisé est proposé pour instancier dynamiquement et à la demande des modules logiciels appelés fonctions de réseau virtuelles (VNF). Cette évolution soulève un ensemble de défis liés au déploiement et à l'exploitation de services, tels que l'orchestration et la gestion, la résilience des services, le contrôle de la qualité de service (QoS), l’approvisionnement des ressources, etc. En outre, la question centrale à résoudre dans le contexte NFV est la suivante : « comment placer et chaîner effacement des fonctions virtuelles d’un service afin de fournir un niveau de qualité demandé par le client tout en optimisant l'utilisation des ressources par le fournisseur de services ? ”.Ainsi, cette thèse étudie la problématique du placement et du chaînage des VNF en tenant compte de certaines exigences de service telles que le délai de bout en bout, la disponibilité du service et la consommation d'énergie, et propose un ensemble d'algorithmes et de mécanismes visant à optimiser le déploiement des services demandés/fournis. Nos contributions dans cette thèse sont triples. Premièrement, nous proposons deux algorithmes de placement et de chaînage de VNF sensibles au délai de bout-en-bout pour des applications temps-réel. Les algorithmes proposés visent à respecter le délai approprié de bout-en-bout qui dépend du service déployé (exemples : VoIP, Streaming, etc.). Deuxièmement, nous présentons une analyse comparative de la disponibilité des services et nous proposons deux mécanismes de placement et de chaînage de VNF pour garantir un niveau prédéfini de disponibilité. L’objectif est de fournir des services résilients en ajustant avec précision les paramètres du schéma de protection (nombre, type, emplacement et taille des instances VNF) nécessaires pour atteindre ce niveau de disponibilité en dépit des défaillances du réseau. Enfin, nous proposons une architecture générale qui explore la possibilité d’étendre le paradigme de la virtualisation à l’Internet des objets (IoT). À cette fin, nous définissons un mécanisme de placement et de chaînage respectant les contraintes énergétiques pour des services IoT. Notre architecture propose de découpler et de virtualiser les fonctionnalités inhérentes à un objet connecté de l’équipement IoT physique. En étendant NFV au domaine IoT, notre solution ouvre de nouvelles perspectives d’application en supportant de nouveaux cas d’usages. / The emergence of Network Function Virtualization (NFV) technology has aroused keen interest to design, manage and deploy network services in a flexible, automated and vendor-agnostic manner. Implementing NFV technology is expected to be a win-win solution for both service providers and costumers. However, this paradigm shift, sparked by NFV, calls for a progressive abandon of network services that are provided as hardware appliance and rather it proposes a fully or partially virtualized environment that offers software modules called Virtual Network Functions (VNFs). This shift rises a set of challenges related to service deployment and operation such as orchestration and management, service resiliency, Quality of Service (QoS) and resource provisioning among others. Furthermore, the core question that needs to be solved within NFV context is “What is the best way to place and chain VNFs that form a service in order to meet Service Level Agreement requirements (costumer side) while optimizing resource usage (service provider side)?”.This thesis investigates the problem of VNF Placement and Chaining considering service requirements such as end-to-end delay, service availability and energy consumption and proposes a set of algorithms and mechanisms that aim to achieve an optimized deployment of the requested/provided services. Our contributions in this thesis are threefold. First, we propose a delay-aware Placement and Chaining algorithms for delay-sensitive applications over NFV networks. The proposed algorithms aim to meet the appropriate end-to-end delay defined according to the deployed service (VoIP, Streaming, etc.). Second, we provide a comprehensive service availability benchmarking and we propose two availability-aware mechanisms for VNFs chain. The aim is to provide resilient service provisioning by fine-tuning the parameters of the protection scheme (the number, the type, the placement and the size of the spare instances) needed to reach a predefined availability level, despite network failures. Finally, we propose a framework architecture that explores the possibility to extend the virtualization paradigm to Internet of Things (IoT). Toward this end, we define an energy-aware Placement and Chaining for IoT services where inherent IoT functionalities are decoupled from specific dedicated IoT devices and instantiated on-demand. By bringing together NFV and IoT paradigms, this extension opens new perspectives and push toward designing new use cases.