Este trabalho apresenta como proposta uma rede sem fio adaptativa, que utiliza o conceito de métricas inter-camadas na escolha das rotas. Para tal, foram realizadas simulações utilizando o programa computacional Network Simulator - NS. Escolheu-se utilizar o protocolo de roteamento OLSR, do inglês Optimized Link State Routing para realizar o cálculo e escolha das rotas, e o padrão IEEE 802.11g foi escolhido para transmissão de dados. As interações entre as camadas foram alteradas, de modo que o valor da relação interferência sinal ruído, do inglês, Signal-to-Interference Noise Ratio - SINR, seja percebida na camada física e repassada para camada de rede. Quando um elemento móvel recebe um pacote de controle de um determinado vizinho, o valor de SINR calculado representa o estado do enlace entre os dois elementos móveis. Assume-se que cada nó possui conhecimento prévio da taxa de transmissão que irá proporcionar a maior vazão possível, de acordo com o estado do enlace. E com base no conhecimento do estado dos enlaces no percurso fim-a-fim, a camada de rede irá buscar e estabelecer o caminho que proporcione a maior vazão possível. E buscando enfatizar os ganhos gerados pelo modelo proposto, os resultados obtidos nas simulações foram comparados com um modelo de rede não adaptativo, utilizando a versão tradicional do protocolo OLSR descrita pela RFC3626. Também verificou-se o desempenho do modelo proposto, em conjunto com algumas técnicas conhecidas e já estabelecidas de combate aos efeitos do desvanecimento. / This work presents a proposal of a wireless adaptive network which chooses its routes based on a cross-layer metric concept. This proposal was conducted by means of computer simulations and more specifically, using the Network Simulator - NS software. Procedures concerning the addiction and establishment of new routes were handled by the well known routing protocol, Optimized Link State Routing protocol - OLSR. The IEEE 802.11g standard was selected to perform all data transmissions. Interactions between the network layers were modified, so the information regarding the signal-to-interference noise ratio (SINR) detected at the physical layer, is delivered directly at the network layer. When a wireless node receives a routing packet from its neighbor, it calculates the SINR value which represents the link state between these two nodes. It is assumed that each wireless node previously knows the transmission rate, which will ensure the highest throughput regarding the state of link. Once a node gathers sufficient information about the link state of each hop across an end-to-end path, the network layer shall be able to calculate the route which offers the highest throughput. And to evaluate the advantages and disadvantages of this proposal, simulation results were compared to a non-adaptive network model, using the traditional version of the OLSR protocol described in the RFC3626. Also the performance of this proposal was evaluated, combined with already known and established fading reduction techniques.

Os backbones IP utilizam protocolos de roteamento do tipo estado do enlace para definir as rotas corretamente. Em situações de mudança na topologia, como uma falha, esses protocolos necessitam de um tempo para reagir e encontrar novas rotas. Durante esse tempo, as rotas ficam instáveis com alta taxa de pacotes perdidos e queda na confiabilidade do backbone. Esse trabalho propõe uma abordagem pró-ativa denominada Esquema de Caminhos Emergenciais Rápidos para auxiliar o protocolo de roteamento OSPF a reduzir a taxa de pacotes perdidos durante esse período. Essa abordagem realiza cálculos reutilizando a base de informações de roteamento do OSPF para gerar esses caminhos emergenciais, que são representados na tabela de encaminhamento através de marcas. Essas marcas são utilizadas então para guiar corretamente os pacotes no contorno de uma falha. Essa abordagem é avaliada em representações de topologias artificiais e reais, e também em simulação para analisar qual o ganho obtido na redução de pacotes perdidos em relação ao OSPF original. A abordagem desenvolvida demonstra resultados bastante satisfatórios em termos de extensão dos caminhos de recuperação utilizados e quantidade de informações extras adicionadas na tabela de encaminhamento em relação à abordagem concorrente. / IP network backbones use link state routing protocols to find correct routes. In face of a topology change, e.g. a failure, these protocols need some time to react to it in order to find new routes. During this time, the routes become unstable, causing high packet loss rate and depreciation of backbone reliability. This work presents a proactive approach named Fast Emergency Paths Schema to help the OSPF routing protocol during the convergence period in order to reduce packet loss rate. The approach conducts calculations reusing the routing information base of the OSPF in order to generate these emergency paths, which are represented in the forwarding table as marks. These are then used to guide the packets to correctly bypass a failure. The approach is evaluated by using various artificial and real topologies, and a simulation is also implemented in order to analyze the packet loss rate reduction in relation to the original OSPF. The analysis yielded satisfactory results in terms of the extension of the recovery paths used and of the amount of extra information added to the forwarding table in relation to the concurrent approach.

Os backbones IP utilizam protocolos de roteamento do tipo estado do enlace para definir as rotas corretamente. Em situações de mudança na topologia, como uma falha, esses protocolos necessitam de um tempo para reagir e encontrar novas rotas. Durante esse tempo, as rotas ficam instáveis com alta taxa de pacotes perdidos e queda na confiabilidade do backbone. Esse trabalho propõe uma abordagem pró-ativa denominada Esquema de Caminhos Emergenciais Rápidos para auxiliar o protocolo de roteamento OSPF a reduzir a taxa de pacotes perdidos durante esse período. Essa abordagem realiza cálculos reutilizando a base de informações de roteamento do OSPF para gerar esses caminhos emergenciais, que são representados na tabela de encaminhamento através de marcas. Essas marcas são utilizadas então para guiar corretamente os pacotes no contorno de uma falha. Essa abordagem é avaliada em representações de topologias artificiais e reais, e também em simulação para analisar qual o ganho obtido na redução de pacotes perdidos em relação ao OSPF original. A abordagem desenvolvida demonstra resultados bastante satisfatórios em termos de extensão dos caminhos de recuperação utilizados e quantidade de informações extras adicionadas na tabela de encaminhamento em relação à abordagem concorrente. / IP network backbones use link state routing protocols to find correct routes. In face of a topology change, e.g. a failure, these protocols need some time to react to it in order to find new routes. During this time, the routes become unstable, causing high packet loss rate and depreciation of backbone reliability. This work presents a proactive approach named Fast Emergency Paths Schema to help the OSPF routing protocol during the convergence period in order to reduce packet loss rate. The approach conducts calculations reusing the routing information base of the OSPF in order to generate these emergency paths, which are represented in the forwarding table as marks. These are then used to guide the packets to correctly bypass a failure. The approach is evaluated by using various artificial and real topologies, and a simulation is also implemented in order to analyze the packet loss rate reduction in relation to the original OSPF. The analysis yielded satisfactory results in terms of the extension of the recovery paths used and of the amount of extra information added to the forwarding table in relation to the concurrent approach.

A large part of today's multi-core chips is interconnect. Increasing communication complexity has made new strategies for interconnects essential such as Network on Chip. Power dissipation in interconnects has become a substantial part of the total power dissipation. Hence, techniques to reduce interconnect power have become a necessity. In this thesis, we present a design methodology that gives values of bus width for interconnect links, frequency of operation for routers, in Network on Chip scenario that satisfy required throughput and dissipate minimal switching power. We develop closed form analytical expressions for the power dissipation, with bus width and frequency as variables and then use Lagrange multiplier method to arrive at the optimal values. To validate our methodology, we implement the router design in 90 nm technology and measure power for various bus widths and frequency combinations. We find that the experimental results are in good agreement with the predicted theoretical results. Further, we present the scenario of an Application Specific System on Chip (ASSoC), where the throughput requirements are different on different links. We show that our analytical model holds in this case also. Then, we present modified version of the solution considered for Chip Multi Processor (CMP) case that can solve the ASSoC scenario also.

Indiana University-Purdue University Indianapolis (IUPUI) / Multi-Protocol Label Switching (MPLS) is an emerging technology which is the initial step for the forthcoming generation of communication. It uses Labels in order to identify the packets unlike the conventional IP Routing Mechanism which uses the routing table at each router to route the packet. MPLS uses the techniques of FRR with the help of RSVP/CR-LDP to overcome the link and/or node failures in the network. On the other hand there are certain limitations/drawbacks of using the above mechanisms for Failure Detection and Recovery which are multiple protocols such as RSVP/CR-LDP over OSPF/IS-IS and complex algorithms to generate backup paths since each router works individually in order to create a backup tunnel. So to overcome the listed limitations, this paper discusses a new technique for MPLS Networks which is Source Routing \cite{48}. Source Routing is the technique in which the source plays the role of directing the packet to the destination and no other router plays the role of routing the packet in the network. Using the OPNET Modeler 17.5 tool for implementing source routing when there is a network failure is performed and the results are compared by implementing RSVP/CR-LDP over the same failed network. The comparative results show that the network performance is best in the case of Source Routing implementation as compared to the RSVP and CR-LDP signaling over the MPLS Networks.

With a new United States Army initiative to exploit commercially developed information technology, there is a heightened interest in using Internet protocols over the military's geosynchronous satellite links. TCP is the dominant Internet protocol used for reliable data exchange, but its own design limits performance when used over long delay network links such as satellites. Initially this research set out to compare TCP with another proposed protocol, the Satellite Transport Protocol (STP). However through a series of tests, we found that STP does not fulfill its claims of increased throughput over TCP and uncovered a flaw in STP's founding research. In addition, this thesis proposes and demonstrates novel performance enhancing techniques that significantly improve transport protocol throughput.

Includes index.

Indiana University-Purdue University Indianapolis (IUPUI) / The study of this thesis is focused on reducing the link failure detection time in OSPF network. When a link failure occurs, OSPF protocol detects it using RouterDeadInterval time. This timer is fired only after a predefined time interval, thus increasing the time of convergence after the link failure. There are previous studies to reduce the RouterDeadInterval time, but they introduce other effects which are discussed later in the thesis. So, a novel approach is proposed in this thesis to reduce the link failure detection time with the help of emerging network architecture Software Defined Networking (SDN) and OpenFlow Protocol.

Les réseaux optiques dynamiques et flexibles font partie des scénarios d'évolution des réseaux de transport optique. Ceux-ci formeront la base de la nouvelle génération des réseaux optiques de demain et permettront le déploiement efficace des services tel que le Cloud Computing. Cette évolution est destinée à apporter flexibilité et automatisation à la couche optique, mais s'accompagne d'une complexité supplémentaire, notamment au niveau de la gestion et de la commande de cette toute nouvelle génération de réseau. Jusqu'à récemment, les protocoles de routage et de signalisation normalisés ont pris en compte plusieurs paramètres physiques tels que l'information spectrale de la bande passante, le format de modulation, et la régénération optique. Cependant, d'autres paramètres sont encore nécessaires (par exemple, les puissances optiques des liens, le gain des amplificateurs) afin de faire fonctionner efficacement de grands réseaux. Dans ce contexte, il y a un besoin d'étudier les réseaux optiques existants ainsi que les différentes méthodes de prise en compte de la couche photonique dans le plan de contrôle. Le but est d'avoir un réseau optique automatique, flexible et programmable, mais surtout efficace de point de vue économique et opérationnel. L'utilisation de la technologie à grille flexible a un impact sur les réseaux optiques existants, où presque tous les équipements devront être remplacés, ce qui entraînera un coût additionnel pour les opérateurs. Dans ce travail, nous étudions les réseaux optiques actuels et évaluons l'impact de la flexibilité sur les infrastructures existantes. Ensuite, nous identifions plusieurs paramètres optiques à contrôler et proposons des extensions protocolaires afin d'intégrer ces paramètres dans un plan de contrôle GMPLS. De plus, nous développons les algorithmes de routage et de signalisation qui permettent la mise en œuvre d'un plan de contrôle efficace qui répond au besoin de la flexibilité. Enfin, l'ensemble de nos propositions et de nos solutions sont évaluées sur plusieurs topologies réseaux avec des modèles de trafic différents dans le but de valider leur pertinence. / Dynamic and flexible optical networks are among the evolution scenarios of the optical transport networks. These form the basis of the new generation of optical networks of tomorrow and enable the effective deployment of services such as cloud computing. This evolution is intended to provide flexibility and automation to the optical layer. However, it results in additional complexity, particularly in terms of the management and control of this new network generation. Until recently, the standardized routing and signaling protocols have been taking into account several optical parameters like the spectral bandwidth information, modulation format, and optical regeneration. However, other parameters (e.g., link optical powers, gain of optical amplifiers) are still required in order to efficiently operate large optical networks. In this context, there is a need to study the existing optical networks and the different integration methods of the photonic layer in a control plane. The goal is to get an automatic optical network that is flexible, programmable, and at the same time efficient from an economical and operational perspective. The use of flexible grid technology has an impact on existing optical networks, where almost all the equipment must be replaced, resulting in an additional cost to network operators. In this work, we study the current optical networks and evaluate the impact of flexibility on the existing infrastructures. Then, we identify several physical parameters to be controlled and propose protocol extensions in order to integrate these parameters in the GMPLS control plane. In addition, we develop the routing and signaling algorithms that allow the implementation of an efficient control plane that addresses the need for flexibility. Finally, the set of our proposals and solutions are evaluated on multiple network topologies with different traffic patterns in order to validate their relevance.