Approved for public release; distribution is unlimited / Virtual Private Networks (VPNs) are designed to use the Transmission Control Protocol (TCP) or User Datagram Protocol (UDP) to establish secure communication tunnels over public Internet. Multipath TCP (MPTCP) extends TCP to allow data to be delivered over multiple network paths simultaneously. This thesis first builds a testbed and investigates the potential of using MPTCP tunnels to increase the goodput of VPN communications and support seamless mobility. Based on the empirical results and an analysis of the MPTCP design in Linux kernels, we further introduce a full-multipath kernel, implementing a basic Multipath UDP (MPUDP) protocol into an existing Linux MPTCP kernel.We demonstrate the MPUDP protocol provides performance improvements over single path UDP tunnels and in some cases MPTCP tunnels. The MPUDP kernel should be further developed to include more efficient scheduling algorithms and path managers to allow better performance and mobility benefits seen with MPTCP. / Outstanding Thesis / Lieutenant, United States Navy

Submitted by Diogo Barreiros (diogo.barreiros@ufba.br) on 2017-06-02T16:07:58Z No. of bitstreams: 1 Dissertação_Cleber_Final.pdf: 7551475 bytes, checksum: 81ec53d1cfbee023ecc28745db6472a1 (MD5) / Approved for entry into archive by Vanessa Reis (vanessa.jamile@ufba.br) on 2017-06-06T14:17:04Z (GMT) No. of bitstreams: 1 Dissertação_Cleber_Final.pdf: 7551475 bytes, checksum: 81ec53d1cfbee023ecc28745db6472a1 (MD5) / Made available in DSpace on 2017-06-06T14:17:04Z (GMT). No. of bitstreams: 1 Dissertação_Cleber_Final.pdf: 7551475 bytes, checksum: 81ec53d1cfbee023ecc28745db6472a1 (MD5) / Os grandes centros de dados atuais tipicamente adotam redund^ancia de servidores e equipamentos de comunica c~ao para aumento de sua con abilidade e disponibilidade. Infraestrutura altamente redundante, contudo, consiste num dos desa os da area devido ao alto consumo de energia. Esta disserta c~ao apresenta a BEEP, uma estrat egia energeticamente e ciente para redes de centro de dados de nidas por software, baseadas na topologia Fat-Tree. Nossa estrat egia, implementada atrav es de uma rede OpenFlow faz uso de m ultiplos caminhos, atrav es do MultiPath TCP { MPTCP e da vis~ao global oferecida por controladores de uma rede de nida por software, para equilibrar e ci^encia energ etica, n vel de redund^ancia dos equipamentos e ganho de desempenho no atendimento as demandas de tr afego. Para alcan car este equil brio, a BEEP procura fazer com que o tr afego de comunica c~ao seja enviado o mais r apido poss vel, utilizando-se da maior quantidade poss vel de caminhos distintos existentes entre a origem o destino de uma comunica c~ao. Desta forma, as interfaces dos comutadores permanecem em estado ocioso na maior parte do tempo e, assim, o consumo energ etico e reduzido. Resultados experimentais em variantes da topologia Fat-Tree demonstraram ganhos de e ci^encia energ etica com a estrat egia na ordem de 21% a 47%, em compara c~ao a outras estrat egias (ECO-RP e GreenCloud), al em de melhoria na utiliza c~ao da largura de banda dispon vel, conforme haja mais caminhos alternativos dispon veis em todos os cen arios avaliados. Al em de construir a BEEP, as demais contribui c~oes trazidas por esta disserta c~ao s~ao: i) o desenvolvimento de um ambiente de prototipa c~ao de aplica c~oes de TCP de m ultiplos caminhos em redes de nidas por software, capaz de mensurar e validar novas propostas para economia de energia baseada em elementos de uma rede de centro de dados; e ii) uma avalia c~ao experimental do TCP de m ultiplos caminhos implementado atrav es de redes de nidas por software para redes de centro de dados.

Multipath TCP (MPTCP) is a new modification of TCP protocol which enables a client to transfer data over multiple paths simultaneously under a single TCP connection, for improved throughput and fault resilience. However, MPTCP is susceptible to some major drawbacks when applied in a wireless network. We found several cases where, despite improving individual MPTCP clients throughput, MPTCP reduces the capacity of the overall wireless network due to the mac level fairness and contention-based access schemes. Additionally, even if the bandwidth improves, employing Multipath TCP (MPTCP) in wireless networks can be energy inecient due to additional energy consumption by multiple interfaces. This creates a dilemma between bandwidth improvement and energy efficiency. This thesis research aims to solve these important issues for MPTCP in the wireless environment. We analyzed the root cause of these drawbacks and identified instances where they can arise. Two novel schemes denoted MPWiFi and kMPTCP, are developed to solve the bandwidth degradation and energy efficiency issues respectively, while maintaining the promised benefitts of MPTCP. The MPWiFi assigns dierent priorities to the subflows and aggressively suppresses some of them based on some design logic. Similarly, kMPTCP adds an additional multipath subflow only if the bandwidth requirement can't be fulllled by single path and the new subflow meets the data rate and signal strength condition. Moreover, kMPTCP keeps additional subflows as long as the signal strength remains in good range and this subflow remain mandatory to provide the necessary bandwidth to the application. These two schemes have been implemented along with Linux Kernel MPTCP implementation. Extensive real-world deployment and NS3 simulation show that the proposed schemes can eectively alleviate the adverse impacts of the MPTCP based multipath access in Wireless networks.

Cette thèse présente une solution pour améliorer la mobilité des réseaux, dans le cadre de communications véhiculaires ainsi que pour la distribution de contenu. Les solutions actuelles pour les communications véhiculaires (c'est-à-dire lorsqu'un réseau est mobile) reposent sur la mise en place de tunnels, permettant également d'utiliser simultanément les différentes interfaces disponibles sur le véhicule (multi-homing). Même avec des tunnels, ces solutions ne sont pas en mesure d'équilibrer le trafic sur les interfaces réseau disponibles, elles ne parviennent pas à tirer partie du multi-homing. De plus, certaines des solutions existantes pour la mobilité de réseau cachent la mobilité aux hôtes connectés au routeur mobile. De fait, cela empêche les hôtes de participer aux décisions relatives au multi-homing, telles que le choix de l'interface réseau à utiliser, ce qui est pourtant utile pour réaliser du routage à moindre coût. Dans cette thèse, nous proposons de combiner un protocole de mobilité réseau (tel que NEMO) avec le protocole de TCP-multivoies (MPTCP), ce qui permet aux nœuds hôtes de participer à la mobilité et au multi-homing. Cette nouvelle combinaison améliore significativement le routage et l'encapsulation de paquets causée par les tunnels. En outre, cela augmente le débit, la tolérance de panne, le temps d'aller-retour et réduit le délai de transmission. La deuxième contribution de ce travail propose une solution de continuité de session pour la distribution de contenu dans les réseaux 5G. Dans le réseau 5G, les équipements d'accès IP seront au plus proche des nœuds terminaux afin d'améliorer l'expérience utilisateur et de réduire la charge de trafic dans le réseau central. Le fait est qu'à un instant donné un terminal ne peut être raccordé qu'à une seule passerelle (SGW/PGW) à la fois. Et comme la passerelle change lors de la mobilité, les sessions en cours seront rompues, impactant les applications temps réelle, le streaming vidéo, les jeux, etc. Pour cela, la thèse présente une solution de continuité de session avec l'aide de TCP-multivoie en bénéficiant du fait que les serveurs de contenu sont stationnaires. / This thesis presents a solution for boosting network mobility in the context of vehicular communications and content distribution in fixed network. Existing solutions for vehicular communications (i.e., network mobility), relies on tunneling in order to use multiple available interfaces on a vehicle. Even with tunnels, these solutions are unable to balance the traffic over available network interfaces thus do not reach the goal to provide optimum multi-homing benefits. Moreover, some of the existing solutions for network mobility, hide the mobility from the hosts connected to the mobile router. This in result inhibits the host nodes from participating in multi-homing related decisions such as interface selection which can be helpful in performing least cost routing. In this thesis, we propose to combine network mobility protocol with MPTCP which enables the host nodes to participate in mobility and multi-homing. This novel combination significantly improves routing and tunneling packet overhead. Moreover it increases throughput, fault tolerance, round-trip time and reduces transmission delay. The second contribution of this work is providing a solution for session continuity in context of content distribution in 5G networks. In 5G network, the IP edges will be closer to the host nodes in order to improve the user experience and reduce traffic load in the core network. The fact that a host can only be connected to a single gateway (SGW/PGW) at a time, would break the ongoing sessions for real time applications like video streaming or gaming during an occurrence of mobility event requiring gateway relocation. The thesis presents the solution for session continuity with the help of multipath TCP by benefiting from the fact that the content servers are stationary.

Despite the huge success and adoption of computer networks in the recent decades, traditional network architecture falls short of some requirements by many applications. One particular shortcoming is the lack of convenient methods for providing quality of service (QoS) guarantee to various network applications. In this dissertation, we explore new Software-Defined Networking (SDN) mechanisms to provision QoS to targeted network flows. Our study contributes to providing QoS support to applications in three aspects. First, we explore using alternative routing paths for selected flows that have QoS requirements. Instead of using the default shortest path used by the current network routing protocols, we investigate using the SDN controller to install forwarding rules in switches that can achieve higher bandwidth. Second, we develop new mechanisms for guaranteeing the latency requirement by those applications depending on timely delivery of sensor data and control signals. The new mechanism pre-allocates higher priority queues in routers/switches and reserves these queues for control/sensor traffic. Third, we explore how to make the applications take advantage of the opportunity provided by SDN. In particular, we study new transmission mechanisms for big data transfer in the cloud computing environment. Instead of using a single TCP path to transfer data, we investigate how to let the application set up multiple TCP paths for the same application to achieve higher throughput. We evaluate these new mechanisms with experiments and compare them with existing approaches.

Made available in DSpace on 2016-06-02T19:07:10Z (GMT). No. of bitstreams: 1 SANDRI_Marcus_2015.pdf: 2702736 bytes, checksum: 227059d931183af24cbcab4cc7a1eb19 (MD5) Previous issue date: 2015-06-10 / Financiadora de Estudos e Projetos / This Master s thesis shows a solution for splitting MPTCP subflows in an Openflow network. MPTCP is a network protocol designed to branch a single TCP connection into many subflows. The main idea is to forward subflows th- rough disjointed paths. Commonly, ECMP protocol is adopted together to split flows through distinct paths. Nevertheless, there are many issues that shows that ECMP is not pareto-optimal, such as: ECMP can easily set two subflows from the same TCP connection on the same path and/or set a distinct forward and back forward route to the same subflow. To solve these issues, it is designed MultiFlow, a module which uses a controller for guarantee multipath routing by setting subflows from the same MPTCP connection so that such subflows are forwarded through distinct paths. MultiFlow is evaluated in experimentation where is analyzed throughput and resilience comparing it with Spanning-Tree (STP) and ECMP. The experiments were done by using Mininet: An OpenFlow emulator for experimenting with a set of topologies. / Esta dissertação apresenta uma solução para distribuir subfluxos Multipath-TCP (MPTCP) em redes OpenFlow. MPTCP é um protocolo desenvolvido para derivar um fluxo TCP em diversos subfluxos e estes serem roteados por caminhos disjuntos ao longo da rede. Convencionalmente, adota-se em conjunto o protocolo Equal-Cost Multipath (ECMP), do qual distribui fluxos de todos os tipos de protocolos ao longo de uma rede com múltiplos caminhos. Entretanto, existem diversas questões que mostram que o ECMP não é um protocolo altamente eficiente. Dentre elas, o ECMP comumente pode alocar dois subfluxos de uma mesma conexão em um mesmo caminho e/ou distribuir um caminho de ida diferente do caminho de volta. A fim de solucionar estes problemas, é desenvolvido o MultiFlow, um módulo para o controlador POX a fim de garantir que subfluxos pertencentes a uma mesma conexão MPTCP possam ser encaminhados em caminhos disjuntos, em uma rede OpenFlow. MultiFlow é validado em experimentos de desempenho onde são analisados taxa de transferência (throughput) e resiliência em experimentos comparativos com os protocolos Spanning-Tree (STP) e ECMP. Para isso, utilizamos o Mininet: Um emulador de rede OpenFlow que permite a criação de diferentes topologias para experimentação.

The market penetration of mobile access devices with multiple network interfaces has increased dramatically over the last few years. As a consequence, the quest for a widespread multi-path transport protocol that takes advantage of all available interfaces simultaneously to increase data throughput and improve robustness, has received considerable attention. One prominent protocol introduced by the IETF is Multipath TCP (MPTCP). MPTCP is an extension to the predominant single-path transport protocol, the Transport Control Protocol (TCP) that enables multihomed devices to aggregate available resources transparently to the applications. Combining multiple radio access technologies, like LTE and Wi-Fi, with diverse characteristics in terms of transmission rates and fluctuations opens for novel challenges that may disrupt and even harm the data throughput. Therefore MPTCP must take path heterogeneity into account. For MPTCP to supersede single-path TCP it is required that MPTCP always achieve at least the throughput of the best individual TCP path. This thesis investigates if MPTCP with uncoupled congestion control fulfills this condition, and if so, how much it improves the throughput. By examining the protocol in a deterministic emulated environment defined by the characteristics of LTE, we conclude two key factors impacting the outcome: the download size and the difference in characteristics between the paths. Our experiments show that MPTCP overall fulfills this task, especially during path homogeneity with near aggregated results. But we also show that MPTCP may decrease data throughput with 16% compared to TCP during path heterogeneity. Hence MPTCP does not always fulfill the goal of throughput. We therefore conclude further intelligence is needed for the packet scheduling mechanism to avoid throughput degradation in the initial phase of a transmission.

No description available.