No description available.

An Origin-Destination (OD) traffic matrix provides a major input to the design, planning and management of a telecommunications network. Since the Internet is being proposed as the principal delivery mechanism for telecommunications traffic at the present time, and this network is not owned or managed by a single entity, there are significant challenges for network planners and managers needing to determine equipment and topology configurations for the various sections of the Internet that are currently the responsibility of ISPs and traditional telcos. Planning of these sub-networks typically requires a traffic matrix of demands that is then used to infer the flows on the administrator's network. Unfortunately, computation of the traffic matrix from measurements of individual flows is extremely difficult due to the fact that the problem formulation generally leads to the need to solve an under-determined system of equations. Thus, there has been a major effort f rom among researchers to obtain the traffic matrix using various inference techniques. The major contribution of this thesis is the development of inference techniques for traffic matrix estimation problem according to three different approaches, viz: (1) deterministic, (2) statistical, and (3) dynamic approaches. Firstly, for the deterministic approach, the traffic matrix estimation problem is formulated as a nonlinear optimization problem based on the generalized Kruithof approach which uses the Kullback distance to measure the probabilistic distance between two traffic matrices. In addition, an algorithm using the Affine scaling method is developed to solve the constrained optimization problem. Secondly, for the statistical approach, a series of traffic matrices are obtained by applying a standard deterministic approach. The components of these matrices represent estimates of the volumes of flows being exchanged between all pairs of nodes at the respective measurement points and they form a stochastic counting process. Then, a Markovian Arrival Process of order two (MAP-2) is applied to model the counting processes formed from this series of estimated traffic matrices. Thirdly, for the dynamic approach, the dual problem of the multi-commodity flow problem is formulated to obtain a set of link weights. The new weight set enables flows to be rerouted along new paths, which create new constraints to overcome the under-determined nature of traffic matrix estimation. Since a weight change disturbs a network, the impact of weight changes on the network is investigated by using simulation based on the well-known ns2 simulator package. Finally, we introduce two network applications that make use of the deterministic and the statistical approaches to obtain a traffic matrix respectively and also describe a scenario for the use of the dynamic approach.

The information on the volume of traffic flowing between all possible origin and destination pairs in an IP network during a given period of time is generally referred to as traffic matrix (TM). This information, which is very important for various traffic engineering tasks, is very costly and difficult to obtain on large operational IP network, consequently it is often inferred from readily available link load measurements. In this thesis, we evaluated 5 TM estimation techniques, namely Tomogravity (TG), Entropy Maximization (EM), Quadratic Programming (QP), Linear Programming (LP) and Neural Network (NN) with gravity and worst-case bound (WCB) initial estimates. We found that the EM technique performed best, consistently, in most of our simulations and that the gravity model yielded better initial estimates than the WCB model. A hybrid of these techniques did not result in considerable decrease in estimation errors. We, however, achieved most significant reduction in errors by combining iterative proportionally-fitted estimates with the EM technique. Therefore, we propose this technique as a viable approach for estimating the traffic matrix of large-scale IP networks.

The information on the volume of traffic flowing between all possible origin and destination pairs in an IP network during a given period of time is generally referred to as traffic matrix (TM). This information, which is very important for various traffic engineering tasks, is very costly and difficult to obtain on large operational IP network, consequently it is often inferred from readily available link load measurements. In this thesis, we evaluated 5 TM estimation techniques, namely Tomogravity (TG), Entropy Maximization (EM), Quadratic Programming (QP), Linear Programming (LP) and Neural Network (NN) with gravity and worst-case bound (WCB) initial estimates. We found that the EM technique performed best, consistently, in most of our simulations and that the gravity model yielded better initial estimates than the WCB model. A hybrid of these techniques did not result in considerable decrease in estimation errors. We, however, achieved most significant reduction in errors by combining iterative proportionally-fitted estimates with the EM technique. Therefore, we propose this technique as a viable approach for estimating the traffic matrix of large-scale IP networks.

Nowadays Network Virtualization provides a new perspective for running multiple, relatively independent applications on same physical network (the substrate network) within shared substrate resources. This method is especially useful for researchers or investigators to get involved into networking field within a lower barrier. As for network virtualization, Virtual Network Mapping (VNM) problem is one of the most important aspects for investigation. Within years of deeply research, several efficient algorithms have been proposed to solve the Virtual Network Mapping problem, however, most of the current mapping algorithm assumes that the virtual network request topology is known or given by customers, in this thesis, a new VNM assumption based on traffic matrix is proposed, also using existing VNM benchmarks, we evaluated the mapping performance based on various metrics, and by comparing the new traffic matrix based VNM algorithm and existing ones, we provide its advantages and shortcomings and optimization to this new VNM algorithm.

Networks-on-Chip (NoC) have been proposed to meet many challenges of modern Systems-on-Chip (SoC) design and manufacturing. At the architectural level, a clean separation of computation and communication helps integration and verification. Networking abstraction of the communication infrastructure also promotes reuse and fast development. But the benefit is most visible when it comes to circuit and physical design. Networks can be made sparse and regular and thus facilitate placement and route. It is also much easier to reach timing and power closure as NoC shield communication details away from complicating analysis. Last but not the least, networks are flexible at the design stage and adaptable post-silicon. Many techniques of tackling process variation and interconnect failure can be built upon NoC. However, when interconnects are time multiplexed in a NoC, the network’s performance will deteriorate if it is not scheduled properly. For a wide range of applications, the traffic on the network can be determined before run-time and offline scheduling offers guaranteed performance and enables simple design. We propose a synthesis flow that takes the data flow graph of the application and a network topology as inputs; and outputs an offline schedule that can be deployed directly to the NoC. We analyze the complexity of combinatorial problems that arise from this context and provide efficient heuristics when polynomial time algorithms are not available assuming P [not equal to] NP. Results on LDPC decoding and FFT designs are compared with previous ones. We further apply our findings to parallel shared memories (PSM) and formalize the PSM architecture and its scheduling problem. An efficient heuristic is derived from our algorithm for unbuffered networks. Another application exemplifies how the NoC can be reprogrammed after silicon is back from fab in order to avoid failed interconnects due to process variation. A simple statistical model is studied and the simulation result is rather interesting. We find out that high performance and yield are not always at conflict if we are able to change the network schedule based on silicon diagnosis. / text

La forte variabilité des trafics est devenue l'un des problèmes majeurs auxquels doivent faire face les gestionnaires d'infrastructures réseau. Dans ces conditions, l'optimisation du routage des flux en se basant uniquement sur une matrice de trafic moyenne estimée en heure de pointe n'est plus pertinente. Les travaux conduits dans cette thèse visent la conception de méthodes d'optimisation dynamiques du routage, adaptant en temps réel les routes utilisées par les flux aux conditions de trafic dans le réseau.Nous étudions tout d'abord le problème d'optimisation des poids OSPF pour le routage intra-domaine dans les réseaux IP, où le trafic est routé le long de plus courts chemins, en fonction des poids des liens. Nous proposons une approche en ligne permettant de reconfigurer dynamiquement les poids OSPF, et donc les routes utilisées, pour répondre aux variations observées du trafic et réduire ainsi le taux de congestion du réseau. L'approche proposée repose sur l'estimation robuste des demandes en trafic des flux à partir de mesures SNMP sur la charge des liens. Les résultats expérimentaux, aussi bien sur des trafics simulés que réels, montrent que le taux de congestion du réseau peut être significativement réduit par rapport à une configuration statique.Dans la même optique, nous nous intéressons également à l'optimisation des réseaux MPLS, qui permettent de gérer l'utilisation des ressources disponibles en affectant un chemin spécifique à chaque LSP. Nous proposons un algorithme inspiré de la théorie des jeux pour déterminer le placement des LSP optimisant un critère de performance non linéaire. Nous établissons la convergence de cet algorithme et obtenons des bornes sur son facteur d'approximation pour plusieurs fonctions de coût. L'intérêt principal de cette technique étant d'offrir des solutions de bonne qualité en des temps de calcul extrêmement réduits, nous étudions son utilisation pour la reconfiguration dynamique du placement des LSP.La dernière partie de cette thèse est consacrée à la conception et au développement d'une solution logicielle permettant le déploiement d'un réseau overlay auto-guérissant et auto-optimisant entre différentes plateformes de cloud computing. La solution est conçue pour ne nécessiter aucun changement des applications. En mesurant régulièrement la qualité des liens Internet entre les centres de données, elle permet de détecter rapidement la panne d'une route IP et de basculer le trafic sur un chemin de secours. Elle permet également de découvrir dynamiquement les chemins dans le réseau overlay qui optimisent une métrique de routage spécifique à l'application. Nous décrivons l'architecture et l'implémentation du système, ainsi que les expériences réalisées à la fois en émulation et sur une plateforme réelle composée de plusieurs centres de données situés dans différents pays. / The high variability of traffic has become one of the major problems faced by network infrastructure managers . Under these conditions, flow route optimization based solely on an average busy hour traffic matrix is no longer relevant. The work done in this thesis aims to design dynamic routing optimization methods, adapting in real time the routes used by the flows to the actual network traffic conditions.We first study the problem of OSPF weight optimization for intra-domain routing in IP networks, where the traffic is routed along shortest paths, according to links weights. We propose an online scheme to dynamically reconfigure the OSPF weights and therefore the routes used, to respond to observed traffic variations and reduce the network congestion rate. The proposed approach is based on robust estimation of flow traffic demands from SNMP measurements on links loads. Experimental results, both on simulated and real traffic data show that the network congestion rate can be significantly reduced in comparison to a static weight configuration.On the same idea, we are also interested in optimizing MPLS networks that manage the available resource utilization by assigning a specific path for each LSP. We propose an algorithm inspired by game theory to determine the LSP placement optimizing a nonlinear performance criterion. We establish the convergence of the algorithm and obtain bounds on its approximation factor for several cost functions. As the main advantage of this technique is to offer good quality solutions in extremely reduced computation times, we are studying its use for dynamic reconfiguration of the LSP placement.The last part of this thesis is devoted to the design and development of a software solution for the deployment of a self-healing and self-optimizing network overlay between different cloud platforms. The solution is designed such that no change is required for client applications. By regularly measuring the quality of Internet links between data centers, it can quickly detect an IP route failure and switch the traffic to a backup path. It also allows to dynamically discover the paths in the overlay network that optimize a routing metric specific to the application. We describe the system architecture and implementation, as well as the experiments in both emulation and real platform composed of several data centers located in different countries

No description available.