Made available in DSpace on 2014-06-12T15:59:17Z (GMT). No. of bitstreams: 2 arquivo4992_1.pdf: 465621 bytes, checksum: beb55c17d095bd73e42ae404d38057fa (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2002 / A crescente demanda e o explosivo crescimento da Internet está impondo novos desafios para a garantia de serviços em termos de performance, confiabilidade e Qualidade de Serviço (QoS). Muitas aplicações de missão crítica que dependem das tecnologias de rede não podem funcionar sem garantias expressas de entrega. Entretanto, as redes de dados atuais não oferecem nenhuma garantia de que as exigências feitas a nível de serviço possam ser garantidas sem algum tipo de degradação a qualquer hora, do dia ou da noite, a despeito de outros usuários da rede. Para atender essas exigências, a infra-estrutura da rede precisa ser melhorada com novas tecnologias que ofereçam aos operadores de rede ferramentas para controlar o comportamento da mesma. Juntas, as capacidades oferecidas pela Engenharia de Tráfego, pelo MPLS (Multiprotocol Label Switching) e pelo DiffServ possibilitam o controle e o balanceamento de carga na rede necessários à entrega de serviço de acordo com contratos personalizados. Este trabalho apresenta o MPLS associado à Engenharia de Tráfego como solução para o problema de alocação ineficiente dos recursos em uma rede e o conseqüente congestionamento provocado por tal problema. O esquema de encaminhamento de pacotes do MPLS é empregado como estratégia para minimizar o congestionamento ou alternativamente maximizar a utilização dos recursos, através da alocação eficiente dos mesmos, garantindo, num ambiente com diferenciação de serviço, uma melhor Qualidade de Serviço em termos de redução na perda de pacotes, no atraso e na variação de atraso, e no aumento da vazão agregada

No description available.

Multiprotocol Label Switching (MPLS) fuses the intelligence of routing with the performance of switching and provides significant benefits to networks with a pure IP architecture as well as those with IP and ATM or a mix of ther Layer 2 technologies. MPLS technology is key to scalable virtual private networks (VPNs) and end-to-end quality of service (QoS), enabling efficient utilization of existing networks to meet future growth. The technology also helps to deliver highly scalable, differentiated end-to-end IP services with simpler configuration, management, and provisioning for both Internet providers and end-users. However, MPLS is a connection-oriented architecture. In case of failure MPLS first has to establish a new label switched path (LSP) and then forward the packets to the newly established LSP. For this reason MPLS has a slow restoration response to a link or node failure on the LSP.The thesis provides a description of MPLS-based architecture as a preferred technology for integrating ATM and IP technologies, followed by a discussion of the motivation for the fast and reliable restoration mechanism in an MPLS network. In this thesis first we address the fast rerouting mechanisms for MPLS networks and then we focus on the problem of packet loss, packet reordering and packet delay for protected LSP in MPLS-based network for a single node/link failure. In order to deliver true service assurance for guaranteed traffic on a protected LSP we use the fast rerouting mechanism with a preplanned alternative LSP. We propose enhancements to current proposals described in extant literature. Our fast rerouting mechanism avoids packet disorder and significantly reduces packet delay during the restoration period.An extension of the Fast Rerouting proposal, called Reliable and Fast Rerouting (RFR), provides some preventive actions for the protected LSP against packet loss during a failure. RFR maintains the same advantages of Fast Rerouting while eliminating packet losses, including those packet losses due to link or node failure (circulating on the failed links), which were considered to be "inevitable" up to now.For the purpose of validating and evaluating the behavior of these proposals a simulation tool was developed. It is based on the NS, a well-known network simulator that is being used extensively in research work. An extension featuring the basic functionality of MPLS (MNS) is also available for the NS, and this is the basis of the developed simulation tool.Simulation results allow the comparison of Fast Rerouting and RFR with previous rerouting proposals.In addition to this we propose a mechanism for multiple failure recovery in an LSP. This proposal combines the path protection, segment protection and local repair methods. In addition to the multiple link/node failure protection, the multiple fault tolerance proposal provides a significant reduction of delay that the rerouted traffic can experience after a link failure, because the repair action is taken close to the point of failure.Then we proceed to address an inherent problem of the preplanned alternative LSP. As alternative LSPs are established together with the protected LSP it may happen that the alternative is not the optimal LSP at the time the failure occurs. To overcome this undesired behavior, we propose the Optimal and Guaranteed Alternative Path (OGAP). The proposal uses a hybrid of fast-rerouting and a dynamic approach to establish the optimal alternative LSP while rerouting the affected traffic using the preplanned alternative LSP. This hybrid approach provides the best of the fast rerouting and the dynamic approaches.At the same time we observed that the protection path becomes in fact unprotected from additional failures after the traffic is rerouted onto it.To address this we propose a guarantee mechanism for protection of the new protected LSP carrying the affected traffic, by establishing an alternative LSP for the rerouted traffic after a failure, avoiding the vulnerability problem for the protected traffic.Finally, we present a further optimization mechanism, adaptive LSP, to enhance the existing traffic engineering for Quality of Services (QoS)provision and improve network resource utilization. The adaptive LSP proposal allows more flexibility in network resource allocation and utilization by adapting the LSP to variations in all network loads,resulting in an enhancement of existing MPLS traffic engineering.

Les algorithmes d'inférence ou d'optimisation possèdent généralement des hyperparamètres qu'il est nécessaire d'ajuster. Nous nous intéressons ici à l'automatisation de cette étape d'ajustement et considérons différentes méthodes qui y parviennent en apprenant en ligne la structure du problème considéré.La première moitié de cette thèse explore l'ajustement des hyperparamètres en apprentissage artificiel. Après avoir présenté et amélioré le cadre générique de l'optimisation séquentielle à base de modèles (SMBO), nous montrons que SMBO s'applique avec succès à l'ajustement des hyperparamètres de réseaux de neurones profonds. Nous proposons ensuite un algorithme collaboratif d'ajustement qui mime la mémoire qu'ont les humains d'expériences passées avec le même algorithme sur d'autres données.La seconde moitié de cette thèse porte sur les algorithmes MCMC adaptatifs, des algorithmes d'échantillonnage qui explorent des distributions de probabilité souvent complexes en ajustant leurs paramètres internes en ligne. Pour motiver leur étude, nous décrivons d'abord l'observatoire Pierre Auger, une expérience de physique des particules dédiée à l'étude des rayons cosmiques. Nous proposons une première partie du modèle génératif d'Auger et introduisons une procédure d'inférence des paramètres individuels de chaque événement d'Auger qui ne requiert que ce premier modèle. Ensuite, nous remarquons que ce modèle est sujet à un problème connu sous le nom de label switching. Après avoir présenté les solutions existantes, nous proposons AMOR, le premier algorithme MCMC adaptatif doté d'un réétiquetage en ligne qui résout le label switching. Nous présentons une étude empirique et des résultats théoriques de consistance d'AMOR, qui mettent en lumière des liens entre le réétiquetage et la quantification vectorielle / Inference and optimization algorithms usually have hyperparameters that require to be tuned in order to achieve efficiency. We consider here different approaches to efficiently automatize the hyperparameter tuning step by learning online the structure of the addressed problem. The first half of this thesis is devoted to hyperparameter tuning in machine learning. After presenting and improving the generic sequential model-based optimization (SMBO) framework, we show that SMBO successfully applies to the task of tuning the numerous hyperparameters of deep belief networks. We then propose an algorithm that performs tuning across datasets, mimicking the memory that humans have of past experiments with the same algorithm on different datasets. The second half of this thesis deals with adaptive Markov chain Monte Carlo (MCMC) algorithms, sampling-based algorithms that explore complex probability distributions while self-tuning their internal parameters on the fly. We start by describing the Pierre Auger observatory, a large-scale particle physics experiment dedicated to the observation of atmospheric showers triggered by cosmic rays. The models involved in the analysis of Auger data motivated our study of adaptive MCMC. We derive the first part of the Auger generative model and introduce a procedure to perform inference on shower parameters that requires only this bottom part. Our model inherently suffers from label switching, a common difficulty in MCMC inference, which makes marginal inference useless because of redundant modes of the target distribution. After reviewing existing solutions to label switching, we propose AMOR, the first adaptive MCMC algorithm with online relabeling. We give both an empirical and theoretical study of AMOR, unveiling interesting links between relabeling algorithms and vector quantization.

No / Fairness in bandwidth resource allocation is highly significance to the advancement of the future generation mobile and wireless technologies. It is likely that restriction of bandwidth due to the employment of some scheduling scheme would not be an appropriate option for the future development of communication systems. However, there is need to consider an implementation that would lead to good network performance and avoid unguaranteed bandwidth delivery. This paper focusses on evaluating the performance of Bandwidth Allocation using Dynamic Label Switching Paths (LSPs) Tunnelling and Label Distribution Protocol (LDP) signalling in Multi-Protocol Label Switching (MPLS) network. This will make provision for bandwidth allocation and reservation possible. An appropriate bandwidth allocation would have a positive impact on throughput as well as the delay. The results of an IP (Internet Protocol) Network without MPLS enabled is compared with MPLS model network. Furthermore, implementation of dynamic and static LSPs models are presented with about 75% decrease in packet delay variation for dynamic LSP when compared from static LSP. In addition, the models of bandwidth estimation, bandwidth allocation, delay and jitter are provided. Performance metrics used in this respect for multimedia services (Voice and Video conferencing) confirm that the modified models are improved in comparison with the baseline, having highest throughput of about 51% increment, and packet delay variation decreases drastically.

Thesis (MSc)--Stellenbosch University, 2003. / ENGLISH ABSTRACT: MPLS-based recovery is intended to effect rapid and complete restoration of traffic affected by a fault in a Multiprotocol Label Switching (MPLS) network. Two MPLS-based recovery models have been proposed: lP re-routing which establishes recovery paths on demand, and protection switching which works with pre-established recovery paths. lP re-routing is robust and frugal since no resources are pre-committed but it is inherently slower than protection switching which is intended to offer high reliability to premium services where fault recovery takes place at the 100 ms time scale. This thesis presents an overview of various recovery techniques and addresses the problem of how to find an in some sense optimal set of pre-established traffic engineered recovery paths, given a network with link capacities and traffic demands. We present and motivate our choice of a nonlinear objective function and optimization method for finding traffic engineered working and recovery paths. A variant of the flow deviation method is used to find and capacitate a set of optimal label switched paths. We present and evaluate two simple methods for computing a set of pre-established traffic engineered recovery paths by using the flow deviation method. / AFRIKAANSE OPSOMMING: MPLS-gebaseerde herstel is daarop gemik om verkeer wat deur 'n fout in 'n Multiprotokol Etiketwisseling (Multiprotocol Label Switching) (MPLS) netwerk geaffekteer is, vinnig en volledig te herstel. Twee MPLS-gebaseerde herstelmodelle is voorgestel: Internetprotokol-herroetering (lP rerouting) wat herstelpaaie op aanvraag tot stand bring, en beskermingsoorskakeling (protection switching) wat met voorafbeplande herstelpaaie werk. IP-herroetering is robuust en voordelig aangesien geen netwerkbronne vooraf gereserveer word nie, maar dit is inherent stadiger as beskermingsoorskakeling wat veronderstel is om 'n hoë graad van betroubaarheid aan belangrike dienste te bied waar die herstel van foute in die 100 ms tydskaal plaasvind. Hierdie tesis verskaf 'n oorsig oor verskeie hersteltegnieke en ondersoek die probleem hoe om 'n optimale versameling van voorafbeplande herstelpaaie te vind, gegee 'n netwerk met skakelkapasiteite (link capacities) en verwagte netwerkverkeer. Ons stel voor en motiveer ons keuse van 'n nie-lineêre objekfunksie en optimeringsmetode om verkeersontwerpde (traffic engineered) aktiewe en herstelpaaie te vind. 'n Variant van die vloeideviasie (flow deviation)-metode word gebruik om 'n optimale versameling van etiketwisseling (label switched) paaie te vind en om 'n optimale hoeveelheid kapasiteit aan die paaie toe te ken. Ons stel voor en evalueer twee eenvoudige metodes om 'n versameling van optimale voorafbeplande herstelpaaie te bereken deur die vloeideviasie-metode toe te pas.

Managed Bandwidth Services (MBSs) use Quality of Service (QoS) guarantees to effectively control traffic flows and reduce network delay. In the past, the provision of MBS in a global manufacturing enterprise was a difficult task for network administrators. However, advances in recently emerging technologies, such as Multiprotocol Label Switching (MPLS), Generalized Multiprotocol Label Switching (GMPLS), Integrated Services (IntServ), Differentiated Services (DiffServ), and Constraint-based Routing (CBR), hold promise to make MBS implementation more manageable. QoS technologies, such as DiffServ and IntServ, offer the benefits of better application performance and delivery of reliable network service. As a consequence of network traffic loads, packet congestion and latency increases still exist and must be addressed by enterprises that intend to support an MBS solution. In this investigation, the author addressed an issue that is faced by many large manufacturing enterprises, i.e., the addition of latency and congestion sensitive traffic such as Voice-over-Internet Protocol (VoIP) to networks with limited bandwidth. The goal of this research was to provide global manufacturing enterprises with a model for bandwidth management in their offices and plants. This model was based on findings from a case study of traffic management at American Standard Companies.

Este trabalho apresenta uma comparação e avaliação das arquiteturas de roteamento IP e IP sobre MPLS. Inicialmente, são apresentados alguns conceitos básicos dos protocolos IP e MPLS, e suas relações com a camada 2 do modelo OSI. Duas características foram analisadas: o processo de encaminhamento e as granularidades para engenharia de tráfego. A medição de desempenho foi feita com computadores Linux realizando a tarefa de roteamento/encaminhamento de datagramas IP em diferentes tipos de redes Ethernet. Com base nos resultados dos testes, é feita uma discussão sobre o desempenho e topologias adequadas para cada arquitetura. / This work presents a comparison and evaluation of IP and the IP over MPLS routing architectures. Initially, some basic concepts of IP and MPLS protocols and their relationship with layer 2 of OSI model are introduced. Two characteristics were analyzed: the forwarding process and traffic engineering granularity. The performance analysis was realized on Linux computers routing/forwarding IP datagramas at different types of Ethernet networks. Considering the results of the tests, a discussion about performance and suitable topologies is made for each architecture.

This research is related to computer networks. In this thesis, three main issues are addressed which affect the performance of any computer network: congestion, efficient resources utilization and link failure. Those issues are related to each other in many situations. Many approaches have been suggested to deal with those issues as well as many solutions were applied. Despite all the improvements of the technology and the proposed solutions, those issues continue to be a burden on the system’s performance. This effect is related to the increase of the Quality of Service (QoS) requirements in modern networks. The basic idea of this research is evolving the intelligence of a conventional computer network when dealing with those issues by adding some features of the Software Defined Networking (SDN). This adoption upgrades the conventional computer network system to be more dynamic and higher self-organizing when dealing with those issues. This idea is applied on a system represented by a computer network that uses the Open Shortest Path First (OSPF) routing protocol. The first improvement deals with the distribution of Internet Protocol (IP) routed flows. The second improvement deals with tunnel establishment that serves Multi-Protocol Label Switching (MPLS) routed flows and the third improvement deals with bandwidth reservation when applying network restoration represented by Fast Re-route (FRR) mechanism to sooth the effect of link failure in OSPF/MPLS routed network. This idea is also applied on another system that uses the Enhanced Interior Gateway Routing Protocol (EIGRP) to improve the performance of its routing algorithm. Adopting the SDN notion is achieved by adding an intelligent controller to the system and creating a dialog of messages between the controller and the conventional routers. This requires upgrading the routers to respond to the new modified system. Our proposed approaches are presented with simulations of different configurations which produce fine results.

The ongoing development of new and demanding Internet applications requires the Internet to deliver better service levels that are significantly better than the best effort service that the Internet currently provides and was built for. These improved service levels include guaranteed delays, jitter and bandwidth. Through extensive research into Quality of Service and Differentiated Service (DiffServ) it has become possible to provide guaranteed services, however this turns out to be inadequate without the application of Traffic Engineering methodologies and principles. Traffic Engineering is an integral part of network operation. Its major goal is to deliver the best performance from an existing service provider's network resources and, at the same time, to enhance a customers' view of network performance. In this thesis, several different traffic engineering methods for optimising the operation of native IP and IP networks employing MPLS are proposed. A feature of these new methods is their fast run times and this opens the way to making them suitable for application in an online traffic engineering environment. For native IP networks running shortest path based routing protocols, we show that an LP-based optimisation based on the well known multi-commodity flow problem can be effective in removing network congestion. Having realised that Internet service providers are now moving towards migrating their networks to the use of MPLS, we have also formulated optimisation methods to traffic engineer MPLS networks by selecting suitable routing paths and utilising the feature of explicit routing contained in MPLS. Although MPLS is capable of delivering traffic engineering across different classes of traffic, network operators still prefer to rely on the proven and simple IP based routing protocols for best effort traffic and only use MPLS to route traffic requiring special forwarding treatment. Based on this fact, we propose a method that optimises the routing patterns applicable to different classes of traffic based on their bandwidth requirements. A traffic engineering comparison study that evaluates the performance of a neural network-based method for MPLS networks and LP-based weight setting approach for shortest path based networks has been performed using a well-known open source network simulator, called ns2. The comparative evaluation is based upon the packet loss probability. The final chapter of the thesis describes the software development of a network management application called OptiFlow which integrates techniques described in earlier chapters including the LP-based weight setting optimisation methodology; it also uses traffic matrix estimation techniques that are required as input to the weight setting models that have been devised. The motivation for developing OptiFlow was to provide a prototype set of tools that meet the congestion management needs of networking industries (ISPs and telecommunications companies - telcos).