Network functions (NFs) hold a key role in networks, offering in-network services, such as enhanced performance, policy enforcement, and security. Traditionally, NFs have been implemented in specialized, thus expensive hardware. To lower the costs of deploying NFs, network operators have adopted network functions virtualization (NFV), by migrating NFs from hardware to software running in commodity servers. Several approaches to NFV have shown that commodity network stacks and drivers (e.g., Linux-based) struggle to keep up with increasing hardware speed. Despite this, popular networking services still rely on these commodity components. Moreover, chaining NFs (also known as service chaining) is challenging due to redundancy in the elements of the chain. This licentiate thesis addresses the performance problems of NFV service chains.The first contribution is a framework that (i) profiles NFV service chains to uncover performance degradation reasons and (ii) leverages the profiler’s data to accelerate these chains, by combining multiplexing of system calls with scheduling strategies. These accelerations improve the cache utilization and thereby the end-to-end latency of chained NFs is reduced by a factor of three. Moreover, the same chains experience a multi-fold latency variance reduction; this result improves the quality of highly-interactive services.The second contribution of this thesis substantially revises the way NFV service chains are realized. NFV service chains are synthesized while eliminating redundant input/output and repeated elements, providing consolidated stateful cross layer packet operations across the chain. This software-based synthesis achieves line-rate 40 Gbps throughput for stateful and long service chains. This performance is 8.5x higher than the performance achieved by the software-based state of the art FastClick framework. Experiments with three example Internet Service Provider-level service chains show that this synthesis approach operates at 40 Gbps, when the classification of these chains is offloaded to an OpenFlow switch. / Nätverksfunktioner (NF) har en nyckelroll i nätverk. De erbjuder tjänster i nätverken som förbättrad prestanda, policy övervakning och säkerhetsfunktioner. Vanligtvis så har NF implementerats med hjälp av specialiserad, och därmed kostsam, hårdvara. Detta har lett till att nätverksoperatörer har börjat använda nätverksfunktionsvirtualisering (NFV) för att minska kostnaden. NFV implementeras genom att NF flyttas från specialiserad hårdvara till mjukvara som kör på vanliga servrar. Flera försök med NFV har visat att vanliga nätverksstackar och drivrutiner (exempelvis Linux baserade) har svårt att erbjuda samma prestanda som hårdvaran gör. Trots detta bygger flera populära nätverkstjänster på NFV. Dessutom är det en utmaning att koppla samman NFV i kedjor, då redundanta operationer utförs. I den här avhandlingen försöker vi lösa prestanda problem kopplade till kedjor av NFV. Det första bidraget i den här avhandlingen är ett ramverk som (i) profilerar NFV kedjor för att hitta orsaker till prestanda problem samt (ii) använder profileringsdata för att förbättra prestandan i kedjorna. Detta görs genom att kombinera multiplexing av systemanrop med planläggningsstrategier. Tillsammans förbättrar dessa lösningar cache användningen och minskar därmed end-to-end latensen i kedjade NFV med en faktor tre. Dessutom minskar vår metod variansen i latens, något som är viktigt för tjänstekvalitén i interaktiva tjänster.Det andra bidraget i den här avhandlingen är en omarbetning av hur kedjade NFV konstrueras. Vi syntetiserar NFV service kedjor genom att ta bort redundanta element och konsoliderar paketoperationer som sträcker sig över flera lager i nätverksstacken. Vår mjukvarubaserade lösning klarar av 40 Gbps genomströmning i en lång kedja. Detta är 8.5 ggr mer än vad som uppnåtts med den tidigare standard lösningen för mjukvara, ramverket FastClick. Vi presenterar experiment med tre servicekedjor för nätverksleverantörer där vår syntetiserade lösning klarar 40 Gbps, när klassificeringen av kedjan görs med hjälp av en OpenFlow switch. / <p>QC 20161103</p> / European Union Horizon 2020 BEhavioural BAsed forwarding (BEBA) / European Research Council (ERC) PROPHET

Os avanços tecnológicos apontam para uma renovação da infraestrutura atual de comunicações ópticas, de modo a torná-la adequada à operação dentro dos novos paradigmas das redes, em que a elasticidade e eficiência espectrais se aliam à alta capacidade de transmissão. Sob o ponto de vista do planejamento de uma operadora de telecomunicação, é desejável que a substituição de equipamentos ocorra de forma mais gradual e que a operação da infraestrutura atual seja otimizada para acomodar a demanda por alta capacidade sem requerer a construção de uma infraestrutura completamente nova. Neste contexto, esta tese investiga estratégias de otimização combinando técnicas que utilizam múltiplas taxas de transmissão (MLR &#8211 Mixed Line Rate) e múltiplos formatos de modulação (MMF &#8211 Multiple Modulation Formats) com foco em um cenário condizente a realidade brasileira, com taxa de transmissão de 10 Gbit/s modulados com a técnica não retorna a zero (NRZ &#8211 non return to zero), migrando para taxa de 40 e/ou 100 Gbit/s. São analisados os benefícios proporcionados com o uso de redes MLR-MMF em comparação com a substituição da rede legada por apenas uma taxa (SLR &#8211 single line rate). A infraestrutura da camada física considerada é uniforme e pode transportar sinais de 10/40/100 Gbit/s, apenas os tipos de transponders são diferentes. Para analisar o desempenho da rede descrita é proposto um modelo de integração entre as ferramentas MatLab e OptiSystem. A primeira é utilizada para definir a rota e a segunda para simular a propagação do sinal óptico na fibra ao longo da rota escolhida. Os valores de taxa de erro de bit (BER &#8211 Bit Error Rate) e a relação sinal ruído óptica (OSNR &#8211 Optical Signal Noise Rate) são armazenados em um banco de dados para uso posterior. Dessa forma diversas topologias podem ser analisadas. Em uma rede real esse tipo de informação pode ser obtido por meio de técnicas de monitoramento óptico (OPM &#8211 Optical Performance Monitoring). Por esse motivo, também são investigados e testados experimentalmente dois métodos de monitoramento da OSNR: i) anulamento da polarização para obter OSNR e ii) monitor multiparâmetro baseado em modulação da polarização em baixa frequência. A partir das análises, concluiu-se que o uso de redes MLR-MMF pode ser uma alternativa para equilibrar o consumo energético e a probabilidade de bloqueio (PB). A opção por esse tipo de rede ajuda na economia energética e mantém a PB em níveis aceitáveis. Além disso, o uso de monitoramento óptico auxilia na obtenção de informações usadas para controlar e gerenciar eficientemente recursos de rede cumprindo os requisitos de qualidade de serviço. / Technological advances point out to an upgrade on the current optical communication infrastructure in order to adequate it to the new networks paradigms, where elasticity and spectral efficiency are associated to the high capacity transmission. From the perspective of a telecom operator planning, it is desirable that the equipment replacement occurs as gradually as possible and that the operation of the current infrastructure is optimized to accommodate the demand for high capacity without requiring the build-upof a completely new infrastructure. In this context, this thesis investigates optimization strategies combining MLR (mixed line rate) and MMF (multiple modulation formats) techniques focusing on a scenario similar to the Brazilian reality, with a transmission rate of 10 Gbit/s NRZ modulated, switching to a rate of 40 and/or 100 Gbit/s. The benefits provided by the use of MMF-MLR network (non return to zero)s compared to the replacing based on a legacy network by only one rate (SLR single line rate) are discussed. The infrastructure of the physical layer is considered uniform and can carry signals 10/40/100 Gbit/s, only the transponder configurations are different. To analyze the network performance we proposed an integration of MATLAB and OptiSystem tools. The first is used to define the route and the second to simulate the propagation of the optical signal in the fiber along the chosen route. The BER and OSNR values are stored in a database for later use. In this way several topologies can be analyzed. In a real network such information may be obtained by optical monitoring techniques (OPM). For this reason, two methods for monitoring OSNR are also investigated: i) the polarization nulling and ii) multiparameter monitor based on modulation of polarization at low frequency. From the analysis it was concluded that the use of MMF-MLR schemes can be an alternative to balance the energy consumption and the blocking probability (BP). The option for this type of network saves energy and helps maintaining BP within acceptable levels. Furthermore, the use of optical monitoring allows the gathering of information used to control and efficiently manage network resources meeting the requirements for quality of service.

Os avanços tecnológicos apontam para uma renovação da infraestrutura atual de comunicações ópticas, de modo a torná-la adequada à operação dentro dos novos paradigmas das redes, em que a elasticidade e eficiência espectrais se aliam à alta capacidade de transmissão. Sob o ponto de vista do planejamento de uma operadora de telecomunicação, é desejável que a substituição de equipamentos ocorra de forma mais gradual e que a operação da infraestrutura atual seja otimizada para acomodar a demanda por alta capacidade sem requerer a construção de uma infraestrutura completamente nova. Neste contexto, esta tese investiga estratégias de otimização combinando técnicas que utilizam múltiplas taxas de transmissão (MLR &#8211 Mixed Line Rate) e múltiplos formatos de modulação (MMF &#8211 Multiple Modulation Formats) com foco em um cenário condizente a realidade brasileira, com taxa de transmissão de 10 Gbit/s modulados com a técnica não retorna a zero (NRZ &#8211 non return to zero), migrando para taxa de 40 e/ou 100 Gbit/s. São analisados os benefícios proporcionados com o uso de redes MLR-MMF em comparação com a substituição da rede legada por apenas uma taxa (SLR &#8211 single line rate). A infraestrutura da camada física considerada é uniforme e pode transportar sinais de 10/40/100 Gbit/s, apenas os tipos de transponders são diferentes. Para analisar o desempenho da rede descrita é proposto um modelo de integração entre as ferramentas MatLab e OptiSystem. A primeira é utilizada para definir a rota e a segunda para simular a propagação do sinal óptico na fibra ao longo da rota escolhida. Os valores de taxa de erro de bit (BER &#8211 Bit Error Rate) e a relação sinal ruído óptica (OSNR &#8211 Optical Signal Noise Rate) são armazenados em um banco de dados para uso posterior. Dessa forma diversas topologias podem ser analisadas. Em uma rede real esse tipo de informação pode ser obtido por meio de técnicas de monitoramento óptico (OPM &#8211 Optical Performance Monitoring). Por esse motivo, também são investigados e testados experimentalmente dois métodos de monitoramento da OSNR: i) anulamento da polarização para obter OSNR e ii) monitor multiparâmetro baseado em modulação da polarização em baixa frequência. A partir das análises, concluiu-se que o uso de redes MLR-MMF pode ser uma alternativa para equilibrar o consumo energético e a probabilidade de bloqueio (PB). A opção por esse tipo de rede ajuda na economia energética e mantém a PB em níveis aceitáveis. Além disso, o uso de monitoramento óptico auxilia na obtenção de informações usadas para controlar e gerenciar eficientemente recursos de rede cumprindo os requisitos de qualidade de serviço. / Technological advances point out to an upgrade on the current optical communication infrastructure in order to adequate it to the new networks paradigms, where elasticity and spectral efficiency are associated to the high capacity transmission. From the perspective of a telecom operator planning, it is desirable that the equipment replacement occurs as gradually as possible and that the operation of the current infrastructure is optimized to accommodate the demand for high capacity without requiring the build-upof a completely new infrastructure. In this context, this thesis investigates optimization strategies combining MLR (mixed line rate) and MMF (multiple modulation formats) techniques focusing on a scenario similar to the Brazilian reality, with a transmission rate of 10 Gbit/s NRZ modulated, switching to a rate of 40 and/or 100 Gbit/s. The benefits provided by the use of MMF-MLR network (non return to zero)s compared to the replacing based on a legacy network by only one rate (SLR single line rate) are discussed. The infrastructure of the physical layer is considered uniform and can carry signals 10/40/100 Gbit/s, only the transponder configurations are different. To analyze the network performance we proposed an integration of MATLAB and OptiSystem tools. The first is used to define the route and the second to simulate the propagation of the optical signal in the fiber along the chosen route. The BER and OSNR values are stored in a database for later use. In this way several topologies can be analyzed. In a real network such information may be obtained by optical monitoring techniques (OPM). For this reason, two methods for monitoring OSNR are also investigated: i) the polarization nulling and ii) multiparameter monitor based on modulation of polarization at low frequency. From the analysis it was concluded that the use of MMF-MLR schemes can be an alternative to balance the energy consumption and the blocking probability (BP). The option for this type of network saves energy and helps maintaining BP within acceptable levels. Furthermore, the use of optical monitoring allows the gathering of information used to control and efficiently manage network resources meeting the requirements for quality of service.

La tolérance aux pannes est une propriété très importante des réseaux optiques de nouvelle génération. Cette thèse aborde la conception des mécanismes de protection contre des pannes liées à la défaillance d’une fibre optique ou à une catastrophe naturelle. Deux systèmes de protection classiques, à savoir la protection par des cycles préconfigurés(p-cycles) et la protection du chemin de secours, sont étudiés pour atteindre une efficacité de protection élevée, tout en considérant le coût de l’équipement optique,la consommation d’énergie et l’utilisation de la ressource spectrale. Ces problèmes de survivabilité sont d’abord formulés en utilisant la programmation linéaire en nombres entiers (PLNE), et ensuite résolus soit par algorithmes heuristiques, soit par une approche de décomposition.La panne d’une seule fibre optique est le scénario le plus courant. Nous allons donc considérer d’abord des pannes liées à la défaillance d’une fibre optique dans les réseaux optiques multi-débit. Pour réduire le coût des transpondeurs, un système de protection par p-cycles de longueur adaptable et peu coûteux est proposé. Spécifiquement, les p cycles de longueur limitée sont conçus pour utiliser un débit approprié en fonction du coût du transpondeur et de la portée de transmission. Un modèle de programmation linéaire en nombres entiers (PLNE) sans énumération des cycles candidats est formulé pour générer directement les p-cycles de coût dépenses d’investissement minimum. De plus, un algorithme GPA (Graph Partitioning in Average) et un algorithme d’estimation des nombres de cycles (EI) sont développés pour rendre le modèle PLNE plus efficace au niveau du temps de calcul. En ce qui concerne la consommation d’énergie des réseaux optiques élastiques résilients,nous proposons d’utiliser un schéma de p-cycles dirigés, efficaces en énergie,pour protéger le trafic asymétrique. En raison de l’avantage de distinguer du volume de trafic dans les deux directions, les p-cycles dirigés consomment peu d’énergie en attribuant de créneaux ou slots du spectre et des formats de modulation différents à chaque direction.Un modèle PLNE est formulé pour minimiser la consommation d’énergie totale sous contraintes de génération du cycle dirigée, d’allocation de spectre, d’adaptation de modulation et de capacité de protection. Pour le passage à l’échelle, le modèle PLNE est décomposé en deux sous-problèmes: une méthode d’énumération de cycles améliorée et un modèle PLNE simplifié pour la sélection des cycles. Nous avons montré que les p-cycles dirigés obtiennent une meilleure performance comparant les p-cyclesiii non-dirigés pour le trafic asymétrique en termes de la consommation d’énergie et de l’utilisation du spectre.Afin d’améliorer l’efficacité d’utilisation du spectre dans réseaux optiques élastiques, une protection par p-cycles (SS-p-cycle) à spectre partagé est proposée. Les SS-p-cycles permettent de réduire l’utilisation du spectre et le taux de fragmentation spectrale en exploitant un partage de spectre spécial entre plusieurs p-cycles ayant des liens communs.Les modèles PLNE est conçus dans les cas "sans" ou "avec" conversion spectrale afin de minimiser l’utilisation du spectre. Ces modèles peuvent obtenir la solution optimale pour un petit réseaux optiques élastiques, et une heuristique efficace est développée pour résoudre les instances à grande échelle. Les résultats de simulations montrent que les SS-p-cycles ont des avantages significatifs pour réduire l’utilisation de la ressource spectrale et la défragmentation des fréquence. De plus, la conversion du spectre aide les SS-p-cycles à acquérir une meilleure utilisation du spectre. / Network survivability is a critical issue for optical networks to maintain resilience against network failures. This dissertation addresses several survivability design issues against single link failure and large-scale disaster failure in optical networks. Twoclassic protection schemes, namely pre-configured Cycles (p-Cycle) protection and path protection, are studied to achieve high protection capacity efficiency while taking intoaccount the equipment cost, power consumption and resource usage. These survivable network design problems are first formulated by mathematical models and then offered scalable solutions by heuristic algorithms or a decomposition approach.We first consider single link failure scenario. To cut the multi-line rates transponderscost in survivable Mixed-Line-Rate (MLR) optical networks, a distance-adaptive andlow Capital Expenditures (CAPEX) cost p-cycle protection scheme is proposed withoutcandidate cycle enumeration. Specifically, path-length-limited p-cycles are designed touse appropriate line rate depending on the transponder cost and transmission reach.A Mixed Integer Linear Programming (MILP) model is formulated to directly generate the optimal p-cycles with the minimum CAPEX cost. Additionally, Graph Partitioning in Average (GPA) algorithm and Estimation of cycle numbers (EI) algorithm are developed to make the proposed MILP model scalable, which are shown to be efficient.Regarding the power consumption in survivable Elastic Optical Networks (EONs),power-efficient directed p-cycle protection scheme for asymmetric traffic is proposed.Owing to the advantage of distinguishing traffic amount in two directions, directedp-cycles consume low power by allocating different Frequency Slots (FSs) and modulation formats for each direction. An MILP model is formulated to minimize total power consumption under constraints of directed cycle generation, spectrum assignment,modulation adaptation and protection capacity allocation. To increase the scalability, the MILP model is decomposed into an improved cycle enumeration and a simplified Integer Linear Programming (ILP) model. We have shown that the directedp-cycles out perform the undirected p-cycles in terms of power consumption and spectrum usage.In order to improve the spectrum usage efficiency in p-cycle protection, a SpectrumShared p-cycle (SS-p-cycle) protection is proposed for survivable EONs with and without spectrum conversion. SS-p-cycles permit to reduce spectrum usage and Spectrum Fragmentation Ratio (SFR) by leveraging potential spectrum sharing among multiplep-cycles that have common link(s). The ILP formulations are designed in both cases of with and without spectrum conversion to minimize the spectrum usage of SS-p-cycleswhich can obtain the optimal solution in small instance, and a time-efficient heuristic algorithm is developed to solve large-scale instances. Simulation results show that SSp-cycles have significant advantages on both spectrum allocation and defragmentation efficiency, and the spectrum conversion does help SS-p-cycle design to acquire better spectrum utilization.

La croissance continue du trafic Internet implique une augmentation de la consommation d'énergie en raison des nombreuses conversions optique à électronique(OEO) requises par les routeurs et les commutateurs. L'utilisation de réseaux transparents pourraient freiner cette croissance incontrôlée, mais le maintien des données dans le domaine optique a deux conséquences néfastes: une accumulation du bruit et des non-linéarités de l'amplification qui dégrade fortement les performances au niveau de la couche physique. et la contrainte de continuité de longueur d'onde (WCC) reflétant la conservation de la longueur d'onde du signal optique dans les réseaux optiques multiplexés en longueur d'onde (WDM) qui dégradent les performances du réseau, notamment sa probabilité de blocage. Les convertisseurs de longueur d'onde (WC) peuvent pallier la contrainte WCC, mais les seuls dispositifs suffisamment matures disponibles dans le commerce sont les WC basés sur OEO (OEO-WC). Cependant, leur coût augmente avec les débits binaires. D'autre part, des convertisseurs de longueur d'onde tout optique (AO-WC) ont été démontrés dans des laboratoires de recherche, avec toutefois une plage de conversion limitée et une dégradation du signal converti.Dans cette thèse, nous concevons la couche de transmission en utilisant deux ensembles de formats de modulation différents avec des plages de débits différentes; et par conséquent différents modèles d'estimation de performance. Au niveau du réseau, nos analyses montrent que la contribution des WC dépend des demandes de trafic servant à l’ordre dans un scénario de planification du réseau; qu'en utilisant des algorithmes fixed-alternate-routing (FAR) ou least-loaded-routing (LLR) et un algorithme d'affectation de longueur d'onde first-fit (FF), les AO-WCs offrent les mêmes améliorations de performances que les OEO-WC. De plus, nous identifions une plage de conversion et une cascadabilité optimale d’AO-WC qui montre que le LLR nécessite un nombre de conversions par canal inférieur au FAR. / The continuous growth of Internet traffic implies an increased power consumption due to the many optical-to-electronic (OEO) conversions required by routers and switches. Transparent networks could curb this uncontrolled growth, but keeping the data in the optical domain has two adverse consequences: physical layer impairments accumulation which strongly degrades the performance due to amplication noise and non-linearities; and the wavelength continuity constraint (WCC) to keep the opticalsignal's wavelength unchanged in wavelength-division-multiplexed (WDM) optical networks which degrades network blocking performance. Wavelength converters (WCs) can alleviate the WCC constraint, but the only commercially available devices are the OEO-based WCs (OEO-WCs), however, their cost increases with bit-rates. On the other hand, all-optical wavelength converters (AO-WCs) have been demonstrated in research laboratories albeit with a limited conversion range and a performance that degrades converted signal's quality.In this thesis, we design the transmission layer using two different modulation formats sets with different bit-rates ranges; and consequently different performance estimation models. At the network level, our analyses show that WCs' contribution depends on traffic demands serving ordering in the online traffic assumption; that using xed-alternate routing (FAR) or least-loaded routing (LLR) algorithms and first-fit (FF) wavelength assignment algorithm, AO-WCs give the same performance enhancement as OEO-WCs. Moreover, we identify an optimum AO-WC conversion range and cascadability which shows that LLR requires lower number of conversions per channel compared to FAR.