<div>Advances in virtualization technologies have revolutionized the design of the core of cellular networks. However, the adoption of microservice design patterns and migration of services from purpose-built hardware to virtualized hardware has adversely affected the delivery of latency-sensitive services.</div><div><br></div><div>In this dissertation, we make a case for cloud-native (microservice container packaged) network functions in the cellular core by proposing domain knowledge-driven, traffic-aware, orchestration frameworks to make network placement decisions. We begin by evaluating the suitability of virtualization technologies for the cellular core and demonstrating that container-driven deployments can significantly outperform other virtualization technologies such as Virtual Machines for control and data plane applications.</div><div><br></div><div>To support the deployment of latency-sensitive applications on virtualized hardware, we propose using Virtual Network Function (VNF) bundles (aggregates) to handle transactions. Specifically, we design Invenio to leverage a combination of network traces and domain knowledge to identify VNFs involved in processing a specific transaction, which are then collocated by a traffic-aware orchestrator. By ensuring that a user request is processed by a single aggregate of collocated VNFs, Invenio can significantly reduce end-to-end latencies and improve user experience.</div><div><br></div><div>Finally, to understand the challenges in using container-driven deployments in real-world applications, we develop and evaluate a novel caller-ID spoofing detection solution in Voice over LTE (VoLTE) calls. Our proposed solution, NASCENT, cross validates the caller-ID used during voice-call signaling with a previously authenticated caller-ID to detect caller-ID spoofing. Our evaluation with traditional and container-driven deployments shows that container-driven deployment can not only support complex cellular services but also outperform traditional deployments.</div><div><br></div>

A Virtualização de Funções de Rede (Network Functions Virtualization - NFV) está mudando o paradigma das redes de telecomunicações. Esta nova tecnologia permite diversas oportunidades de inovações e possibilita o desenvolvimento de novos modelos de negócio. Em relação às redes NFV, os provedores de serviços têm a oportunidade de criar modelos de negócio que permitam aos clientes contratarem Funções de Rede Virtualizadas (Virtual Network Functions - VNFs) que proveem diferentes serviços de rede (e.g., Firewall, NAT e transcoders). Porém, nestes modelos, a quantidade de informações a serem gerenciadas cresce rapidamente. Baseado nisso, os operadores de rede devem ser capazes de entender e manipular uma grande quantidade de informação para gerenciar, de forma efetiva, as redes NFV. Para enfrentar esse problema, introduzimos uma plataforma de visualização denominada VISION, a qual tem como principal objetivo ajudar os operadores de rede na identificação da causa raiz de problemas em NFV. Para isso, propusemos: (i) uma abordagem para coleta e organização de dados do ambiente NFV gerenciado; (ii) cinco diferentes visualizações que auxiliam nas tarefas de gerenciamento de NFV como, por exemplo, no processo de identificação de problemas em VNFs e no planejamento de negócios e (iii) um modelo baseado em templates que suporta o desenvolvimento e o reuso de visualizações. Para fins de avaliação desta dissertação, foi desenvolvido um protótipo da plataforma VISION e de todas as visualizações propostas. Após, conduzimos um conjunto de casos de estudo para prover evidências sobre a viabilidade e utilidade de nossas visualizações. Os diferentes casos analisados, abordam por exemplo, a identificação de problemas na alocação de VNFs que estão impactando no desempenho do serviço oferecido e também na investigação de prioridades de investimento para suprir as demandas dos clientes da rede. Por fim, apresentamos uma avaliação de usabilidade realizada juntamente a especialistas em redes de computadores para avaliar os recursos e benefícios da plataforma VISION. Os resultados obtidos demonstram que nossas visualizações possibilitam ao operador de rede um rápido e fácil acesso às informações importantes para o gerenciamento de redes NFV, assim facilitando a obtenção de insights para a identificação de problemas complexos no contexto de redes NFV. Além disso, os resultados demonstram uma avaliação positiva por especialistas sobre os aspectos gerais de usabilidade do protótipo desenvolvido. / Network Functions Virtualization (NFV) is driving a paradigm shift in telecommunications networks and computer networks, by fostering new business models and creating innovation opportunities. In NFV-enabled networks, service providers have the opportunity to build a business model where tenants can purchase Virtual Network Functions (VNFs) that provide distinct network services and functions (e.g., Firewall, NAT, and transcoders). However, the amount of managed data grows in a fast pace. The network operator must understand and manipulate many data to effectively manage the network. To tackle this problem, we introduce VISION, a platform based on visualizations techniques to help network operators to determine the cause of not obvious problems. For this, we provide: (i) an approach to collect and organize data from the NFV environments; (ii) five distinct visualizations that can aid in NFV management tasks, such as in the process of identifying VNFs problems and planning of NFV-enabled businesses; and (iii) a template model that supports new visualization applications. To evaluate our work, we implemented a prototype of VISION platform and each of the proposed visualizations. We then conducted distinct case studies to provide evidence of the feasibility of our visualizations. These case studies cover different scenarios, such as the identification of misplacement of VNFs that are generating bottlenecks in a forwarding graph and the investigation of investment priorities to supply tenants demands. Finally, we present a usability evaluation with network operators to indicate the benefits of the VISION platform. The results obtained show that our visualizations allow the operator to access relevant information and have insights to identify not obvious problems in the context of NFV-enabled networks. In addition, we received positive feedback about general usability aspects related to our prototype.

A Virtualização de Funções de Rede (Network Functions Virtualization - NFV) está mudando o paradigma das redes de telecomunicações. Esta nova tecnologia permite diversas oportunidades de inovações e possibilita o desenvolvimento de novos modelos de negócio. Em relação às redes NFV, os provedores de serviços têm a oportunidade de criar modelos de negócio que permitam aos clientes contratarem Funções de Rede Virtualizadas (Virtual Network Functions - VNFs) que proveem diferentes serviços de rede (e.g., Firewall, NAT e transcoders). Porém, nestes modelos, a quantidade de informações a serem gerenciadas cresce rapidamente. Baseado nisso, os operadores de rede devem ser capazes de entender e manipular uma grande quantidade de informação para gerenciar, de forma efetiva, as redes NFV. Para enfrentar esse problema, introduzimos uma plataforma de visualização denominada VISION, a qual tem como principal objetivo ajudar os operadores de rede na identificação da causa raiz de problemas em NFV. Para isso, propusemos: (i) uma abordagem para coleta e organização de dados do ambiente NFV gerenciado; (ii) cinco diferentes visualizações que auxiliam nas tarefas de gerenciamento de NFV como, por exemplo, no processo de identificação de problemas em VNFs e no planejamento de negócios e (iii) um modelo baseado em templates que suporta o desenvolvimento e o reuso de visualizações. Para fins de avaliação desta dissertação, foi desenvolvido um protótipo da plataforma VISION e de todas as visualizações propostas. Após, conduzimos um conjunto de casos de estudo para prover evidências sobre a viabilidade e utilidade de nossas visualizações. Os diferentes casos analisados, abordam por exemplo, a identificação de problemas na alocação de VNFs que estão impactando no desempenho do serviço oferecido e também na investigação de prioridades de investimento para suprir as demandas dos clientes da rede. Por fim, apresentamos uma avaliação de usabilidade realizada juntamente a especialistas em redes de computadores para avaliar os recursos e benefícios da plataforma VISION. Os resultados obtidos demonstram que nossas visualizações possibilitam ao operador de rede um rápido e fácil acesso às informações importantes para o gerenciamento de redes NFV, assim facilitando a obtenção de insights para a identificação de problemas complexos no contexto de redes NFV. Além disso, os resultados demonstram uma avaliação positiva por especialistas sobre os aspectos gerais de usabilidade do protótipo desenvolvido. / Network Functions Virtualization (NFV) is driving a paradigm shift in telecommunications networks and computer networks, by fostering new business models and creating innovation opportunities. In NFV-enabled networks, service providers have the opportunity to build a business model where tenants can purchase Virtual Network Functions (VNFs) that provide distinct network services and functions (e.g., Firewall, NAT, and transcoders). However, the amount of managed data grows in a fast pace. The network operator must understand and manipulate many data to effectively manage the network. To tackle this problem, we introduce VISION, a platform based on visualizations techniques to help network operators to determine the cause of not obvious problems. For this, we provide: (i) an approach to collect and organize data from the NFV environments; (ii) five distinct visualizations that can aid in NFV management tasks, such as in the process of identifying VNFs problems and planning of NFV-enabled businesses; and (iii) a template model that supports new visualization applications. To evaluate our work, we implemented a prototype of VISION platform and each of the proposed visualizations. We then conducted distinct case studies to provide evidence of the feasibility of our visualizations. These case studies cover different scenarios, such as the identification of misplacement of VNFs that are generating bottlenecks in a forwarding graph and the investigation of investment priorities to supply tenants demands. Finally, we present a usability evaluation with network operators to indicate the benefits of the VISION platform. The results obtained show that our visualizations allow the operator to access relevant information and have insights to identify not obvious problems in the context of NFV-enabled networks. In addition, we received positive feedback about general usability aspects related to our prototype.

A Virtualização de Funções de Rede (Network Functions Virtualization - NFV) está mudando o paradigma das redes de telecomunicações. Esta nova tecnologia permite diversas oportunidades de inovações e possibilita o desenvolvimento de novos modelos de negócio. Em relação às redes NFV, os provedores de serviços têm a oportunidade de criar modelos de negócio que permitam aos clientes contratarem Funções de Rede Virtualizadas (Virtual Network Functions - VNFs) que proveem diferentes serviços de rede (e.g., Firewall, NAT e transcoders). Porém, nestes modelos, a quantidade de informações a serem gerenciadas cresce rapidamente. Baseado nisso, os operadores de rede devem ser capazes de entender e manipular uma grande quantidade de informação para gerenciar, de forma efetiva, as redes NFV. Para enfrentar esse problema, introduzimos uma plataforma de visualização denominada VISION, a qual tem como principal objetivo ajudar os operadores de rede na identificação da causa raiz de problemas em NFV. Para isso, propusemos: (i) uma abordagem para coleta e organização de dados do ambiente NFV gerenciado; (ii) cinco diferentes visualizações que auxiliam nas tarefas de gerenciamento de NFV como, por exemplo, no processo de identificação de problemas em VNFs e no planejamento de negócios e (iii) um modelo baseado em templates que suporta o desenvolvimento e o reuso de visualizações. Para fins de avaliação desta dissertação, foi desenvolvido um protótipo da plataforma VISION e de todas as visualizações propostas. Após, conduzimos um conjunto de casos de estudo para prover evidências sobre a viabilidade e utilidade de nossas visualizações. Os diferentes casos analisados, abordam por exemplo, a identificação de problemas na alocação de VNFs que estão impactando no desempenho do serviço oferecido e também na investigação de prioridades de investimento para suprir as demandas dos clientes da rede. Por fim, apresentamos uma avaliação de usabilidade realizada juntamente a especialistas em redes de computadores para avaliar os recursos e benefícios da plataforma VISION. Os resultados obtidos demonstram que nossas visualizações possibilitam ao operador de rede um rápido e fácil acesso às informações importantes para o gerenciamento de redes NFV, assim facilitando a obtenção de insights para a identificação de problemas complexos no contexto de redes NFV. Além disso, os resultados demonstram uma avaliação positiva por especialistas sobre os aspectos gerais de usabilidade do protótipo desenvolvido. / Network Functions Virtualization (NFV) is driving a paradigm shift in telecommunications networks and computer networks, by fostering new business models and creating innovation opportunities. In NFV-enabled networks, service providers have the opportunity to build a business model where tenants can purchase Virtual Network Functions (VNFs) that provide distinct network services and functions (e.g., Firewall, NAT, and transcoders). However, the amount of managed data grows in a fast pace. The network operator must understand and manipulate many data to effectively manage the network. To tackle this problem, we introduce VISION, a platform based on visualizations techniques to help network operators to determine the cause of not obvious problems. For this, we provide: (i) an approach to collect and organize data from the NFV environments; (ii) five distinct visualizations that can aid in NFV management tasks, such as in the process of identifying VNFs problems and planning of NFV-enabled businesses; and (iii) a template model that supports new visualization applications. To evaluate our work, we implemented a prototype of VISION platform and each of the proposed visualizations. We then conducted distinct case studies to provide evidence of the feasibility of our visualizations. These case studies cover different scenarios, such as the identification of misplacement of VNFs that are generating bottlenecks in a forwarding graph and the investigation of investment priorities to supply tenants demands. Finally, we present a usability evaluation with network operators to indicate the benefits of the VISION platform. The results obtained show that our visualizations allow the operator to access relevant information and have insights to identify not obvious problems in the context of NFV-enabled networks. In addition, we received positive feedback about general usability aspects related to our prototype.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第24940号 / 情博第851号 / 新制||情||142(附属図書館) / 京都大学大学院情報学研究科通信情報システム専攻 / (主査)教授 大木 英司, 教授 原田 博司, 教授 伊藤 孝行 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

La densification de réseau à l'aide de petites cellules massivement déployées sur les zones macro-cellules, représente une solution prometteuse pour les réseaux mobiles 5G avenir pour faire face à l'augmentation du trafic mobile. Afin de simplifier la gestion de l'hétérogène du réseau d'accès radio (Radio Access Network RAN) qui résulte du déploiement massif de petites cellules, des recherches récentes et des études industrielles ont favorisé la conception de nouvelles architectures de RAN centralisés appelés comme Cloud-RAN (C-RAN), ou RAN virtuel (V-RAN), en incorporant les avantages du cloud computing et Network Functions Virtualization (NFV). Le projet de DynaRoC vise l'élaboration d'un cadre théorique de l'orchestration de ressources pour les C-RAN et dériver les limites de performance fondamentaux ainsi que les arbitrages entre les différents paramètres du système, et la conception de mécanismes d'orchestration de ressources dynamiques sur la base des conclusions théoriques à atteindre un équilibre de performance souhaité, en tenant compte des différents défis de conception. Le doctorant va étudier les mécanismes d'optimisation des ressources novatrices pour favoriser le déploiement de C-RAN, améliorer leur performance exploitant la technologie Network Functions Virtualization / Network densification using small cells massively deployed over the macro-cell areas, represents a promising solution for future 5G mobile networks to cope with mobile traffic increase. In order to simplify the management of the heterogeneous Radio Access Network (RAN) that results from the massive deployment of small cells, recent research and industrial studies have promoted the design of novel centralized RAN architectures termed as Cloud-RAN (C-RAN), or Virtual RAN (V-RAN), by incorporating the benefits of cloud computing and Network Functions Virtualization (NFV). The DynaRoC project aims at (1) developing a theoretical framework of resource orchestration for C-RAN and deriving the fundamental performance limits as well as the tradeoffs among various system parameters, and (2) designing dynamic resource orchestration mechanisms based on the theoretical findings to achieve a desired performance balance, by taking into account various design challenges. The PhD student will investigate innovative resource optimization mechanisms to foster the deployment of C-RANs, improving their performance exploiting the enabling Network Functions Virtualization technology

This is a Masters student Final Dissertation / In this project, two tests were performed. On the first test, Mininet-WiFi was used to simulate a Software Defined Network to demonstrate Mininet-WiFi’ s ability to be used as the Software Defined Network emulator which can also be integrated to the existing network using a Network Virtualized Function (NVF). A typical organization’s computer network was simulated which consisted of a website hosted on the LAMP (Linux, Apache, MySQL, PHP) virtual machine, and an F5 application delivery controller (ADC) which provided load balancing of requests sent to the web applications. A website page request was sent from the virtual stations inside Mininet-WiFi. The request was received by the application delivery controller, which then used round robin technique to send the request to one of the web servers on the LAMP virtual machine. The web server then returned the requested website to the requesting virtual stations using the simulated virtual network. The significance of these results is that it presents Mininet-WiFi as an emulator, which can be integrated into a real programmable networking environment offering a portable, cost effective and easily deployable testing network, which can be run on a single computer. These results are also beneficial to modern network deployments as the live network devices can also communicate with the testing environment for the data center, cloud and mobile provides. On the second test, a Software Defined Network was created in Mininet using python script. An external interface was added to enable communication with the network outside of Mininet. The amazon web services elastic computing cloud was used to host an OpenDaylight controller. This controller is used as a control plane device for the virtual switch within Mininet. In order to test the network, a webserver hosted on the Emulated Virtual Environment – Next Generation (EVENG) software is connected to Mininet. EVE-NG is the Emulated Virtual Environment for networking. It provides tools to be able to model virtual devices and interconnect them with other virtual or physical devices. The OpenDaylight controller was able to create the flows to facilitate communication between the hosts in Mininet and the webserver in the real-life network / The University of South Africa The University of Johannesburg / College of Engineering, Science and Technology

The NetCOPE framework has proven itself as a viable framework for rapid development of hardware accelerated wire-speed network applications using Network Functions Virtualization (NFV). To meet the current and future requirements of such applications the NetCOPE platform has to catch up with upcoming 400 Gigabit Ethernet. Otherwise, it may become deprecated in following years. Catching up with 400 Gigabit Ethernet brings many challenges bringing necessity of completely different way of thinking. Multiple network packets have to be processed each clock cycle requiring a new concept of processing. Advanced memory management is used to ensure constant memory complexity with respect to the number of DMA channels without any impact on performance. Thanks to that, even more than 256 completely independent DMA channels are feasible with current technology. A lot of effort was made to create the framework as generic as possible allowing deployment of 400 Gigabit Ethernet and beyond. Emphasis is put on communication between the framework and host computer via PCI Express technology. Multiple Ethernet ports are also considered. The proposed system is prepared to be deployed on the family of COMBO cards, used as a reference platform.

In this project, two tests were performed. On the first test, Mininet-WiFi was used to simulate a Software Defined Network to demonstrate Mininet-WiFi’ s ability to be used as the Software Defined Network emulator which can also be integrated to the existing network using a Network Virtualized Function (NVF). A typical organization’s computer network was simulated which consisted of a website hosted on the LAMP (Linux, Apache, MySQL, PHP) virtual machine, and an F5 application delivery controller (ADC) which provided load balancing of requests sent to the web applications. A website page request was sent from the virtual stations inside Mininet-WiFi. The request was received by the application delivery controller, which then used round robin technique to send the request to one of the web servers on the LAMP virtual machine. The web server then returned the requested website to the requesting virtual stations using the simulated virtual network. The significance of these results is that it presents Mininet-WiFi as an emulator, which can be integrated into a real programmable networking environment offering a portable, cost effective and easily deployable testing network, which can be run on a single computer. These results are also beneficial to modern network deployments as the live network devices can also communicate with the testing environment for the data center, cloud and mobile provides. On the second test, a Software Defined Network was created in Mininet using python script. An external interface was added to enable communication with the network outside of Mininet. The amazon web services elastic computing cloud was used to host an OpenDaylight controller. This controller is used as a control plane device for the virtual switch within Mininet. In order to test the network, a webserver hosted on the Emulated Virtual Environment – Next Generation (EVENG) software is connected to Mininet. EVE-NG is the Emulated Virtual Environment for networking. It provides tools to be able to model virtual devices and interconnect them with other virtual or physical devices. The OpenDaylight controller was able to create the flows to facilitate communication between the hosts in Mininet and the webserver in the real-life network. / Electrical and Mining Engineering

<p>Online decision making with switching costs has received considerable attention in many practical problems that face uncertainty in the inputs and key problem parameters. Because of the switching costs that penalize the change of decisions, making good online decisions under such uncertainty is known to be extremely challenging. This thesis aims at providing new online algorithms with strong performance guarantees to address this challenge.</p> <p><br></p> <p>In part 1 and part 2 of this thesis, motivated by Network Functions Virtualization and smart grid, we study competitive online convex optimization with switching costs. Specifically, in part 1, we focus on the setting with an uncertainty set (one type of prediction) and hard infeasibility constraints. We develop new online algorithms that can attain optimized competitive ratios, while ensuring feasibility at all times. Moreover, we design a robustification procedure that helps these algorithms obtain good average-case performance simultaneously. In part 2, we focus on the setting with look-ahead (another type of prediction). We provide the first algorithm that attains a competitive ratio that not only decreases to 1 as the look-ahead window size increases, but also remains upper-bounded for any ratio between the switching-cost coefficient and service-cost coefficient.</p> <p><br></p> <p>In part 3 of this thesis, motivated by edge computing with artificial intelligence, we study bandit learning with switching costs where, in addition to bandit feedback, full feedback can be requested at a cost. We show that, when only 1 arm can be chosen at a time, adding costly full-feedback is not helpful in fundamentally reducing the Θ(<em>T</em>2/3) regret over a time-horizon <em>T</em>. In contrast, when 2 (or more) arms can be chosen at a time, we provide a new online learning algorithm that achieves a significantly smaller regret equal to <em>O</em>(√<em>T</em>), without even using full feedback. To the best of our knowledge, this type of sharp transition from choosing 1 arm to choosing 2 (or more) arms has never been reported in the literature.</p>