Lau Ka Ming. / Thesis submitted in: August 2005. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2006. / Includes bibliographical references (leaves 69-72). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgements --- p.iii / Table of Contents --- p.iv / List of Figures --- p.vi / List of Tables --- p.viii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Introduction --- p.1 / Chapter 1.2 --- Wireless Ad Hoc Networks --- p.2 / Chapter 1.2.1 --- Wireless Sensor Network --- p.3 / Chapter 1.2.2 --- IEEE802.11 Ad Hoc Network --- p.3 / Chapter 1.2.3 --- Bluetooth Personal Area Network --- p.4 / Chapter 1.3 --- Power Saving in Wireless Ad Hoc Networks --- p.4 / Chapter 1.4 --- Contributions of the Thesis --- p.8 / Chapter 1.5 --- Outline of the Thesis --- p.9 / Chapter 2 --- Power Saving Mechanisms in Wireless Ad hoc Networks --- p.10 / Chapter 2.1 --- Recent Research Proposals --- p.10 / Chapter 2.1.1 --- Synchronous Power Saving Schemes --- p.11 / Chapter 2.1.2 --- Asynchronous Power Saving Schemes --- p.12 / Chapter 2.2 --- Existing Standards --- p.17 / Chapter 2.2.1 --- IEEE802.1l Ad Hoc Power Saving Mode --- p.17 / Chapter 2.2.2 --- Bluetooth Low Power Modes --- p.20 / Chapter 3 --- Analytical Framework for Designing Synchronous Wakeup Patterns --- p.22 / Chapter 3.1 --- System Model --- p.23 / Chapter 3.1.1 --- Vacation Model --- p.23 / Chapter 3.1.2 --- Optimal Wakeup Pattern --- p.25 / Chapter 3.2 --- Analytical analysis of different wakeup patterns --- p.27 / Chapter 3.2.1 --- Exhaustive Wakeup Pattern --- p.27 / Chapter 3.2.2 --- Gated Wakeup Pattern --- p.31 / Chapter 3.2.3 --- Gated Wakeup With Constant Cycle Time --- p.34 / Chapter 3.3 --- Discussion of results --- p.43 / Chapter 3.3.1 --- Performances impacts of various system parameters --- p.43 / Chapter 3.3.2 --- Performances comparison of different wakeup patterns --- p.47 / Chapter 3.4 --- Chapter Summary --- p.48 / Chapter 4 --- An improved IEEE802.1l Power Saving Mode --- p.49 / Chapter 4.1 --- Related Proposals --- p.50 / Chapter 4.2 --- Proposed Scheme --- p.52 / Chapter 4.2.1 --- Overview --- p.52 / Chapter 4.2.2 --- Beacon Sending Station --- p.53 / Chapter 4.2.3 --- Beacon Receiving Station --- p.55 / Chapter 4.2.4 --- Computing the Transmission Schedule --- p.55 / Chapter 4.2.5 --- Data Transmission Specifications --- p.56 / Chapter 4.2.6 --- Failure Conditions --- p.58 / Chapter 4.3 --- Performances Evaluation --- p.58 / Chapter 4.3.1 --- Simulation Model --- p.60 / Chapter 4.3.2 --- Simulation Results --- p.60 / Chapter 4.4 --- Chapter Summary --- p.64 / Chapter 5 --- Conclusion --- p.66

Thesis (Ph.D.) -- University of Texas at Arlington, 2008.

Present-day datacenter networks (DCNs) are designed to achieve full bisection bandwidth in order to provide high network throughput and server agility. However, the average utilization of typical DCN infrastructure is below 10% for significant time intervals. As a result, energy is wasted during these periods. In this thesis we analyze traffic behavior of datacenter networks using traces as well as simulated models. Based on the insight developed, we present techniques to reduce energy waste by making energy use scale linearly with load. The solutions developed are analyzed via simulations, formal analysis, and prototyping. The impact of our work is significant because the energy savings we obtain for networking infrastructure of DCNs are near optimal. A key finding of our traffic analysis is that network switch ports within the DCN are grossly under-utilized. Therefore, the first solution we study is to modify the routing within the network to force most traffic to the smallest of switches. This increases the hop count for the traffic but enables the powering off of many switch ports. The exact extent of energy savings is derived and validated using simulations. An alternative strategy we explore in this context is to replace about half the switches with fewer switches that have higher port density. This has the effect of enabling even greater traffic consolidation, thus enabling even more ports to sleep. Finally, we explore a third approach in which we begin with end-to-end traffic models and incrementally build a DCN topology that is optimized for that model. In other words, the network topology is optimized for the potential use of the datacenter. This approach makes sense because, as other researchers have observed, the traffic in a datacenter is heavily dependent on the primary use of the datacenter. A second line of research we undertake is to merge traffic in the analog domain prior to feeding it to switches. This is accomplished by use of a passive device we call a merge network. Using a merge network enables us to attain linear scaling of energy use with load regardless of datacenter traffic models. The challenge in using such a device is that layer 2 and layer 3 protocols require a one-to-one mapping of hardware addresses to IP (Internet Protocol) addresses. We overcome this problem by building a software shim layer that hides the fact that traffic is being merged. In order to validate the idea of a merge network, we build a simple mere network for gigabit optical interfaces and demonstrate correct operation at line speeds of layer 2 and layer 3 protocols. We also conducted measurements to study how traffic gets mixed in the merge network prior to being fed to the switch. We also show that the merge network uses only a fraction of a watt of power, which makes this a very attractive solution for energy efficiency. In this research we have developed solutions that enable linear scaling of energy with load in datacenter networks. The different techniques developed have been analyzed via modeling and simulations as well as prototyping. We believe that these solutions can be easily incorporated into future DCNs with little effort.

Orientador: Nelson Luis Saldanha da Fonseca / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-25T09:43:36Z (GMT). No. of bitstreams: 1 RodriguezBrljevich_Esteban_M.pdf: 2281259 bytes, checksum: 12557ac80a34c2bff2547f1f2aff1eaa (MD5) Previous issue date: 2013 / Resumo: A virtualização de redes é uma tecnologia promissora para a Internet do futuro, já que facilita a implementação de novos protocolos e aplicações sem a necessidade de alterar o núcleo da rede. Um passo chave para instanciar redes virtuais é a alocação de recursos físicos para elementos virtuais (roteadores e enlaces). A fim de contribuir para o esforço global de poupança de energia, a escolha de recursos físicos para instanciar uma rede virtual deveria minimizar o consumo de energia rede. No entanto, esta não é uma tarefa trivial, já que requerimentos de QoS devem ser atingidos. A busca da solução ótima deste problema é NP-difícil. O mapeamento de redes virtuais em substratos de rede físicos em cenários de alocaç?o e desalocaç?o de redes virtuais pode não levar a um consumo mínimo de energia devido à dinâmica das atribuições dos elementos virtuais previamente alocados. Tal dinâmica pode levar à subutilização da rede substrato. Para reduzir os efeitos negativos desta dinâmica, técnicas tais como a migração de redes virtuais em tempo real podem ser empregadas para rearranjar as redes virtuais previamente mapeadas para poupar energia. Esta dissertação apresenta um conjunto de novos algoritmos para o mapeamento de redes virtuais em substratos de rede com o objetivo de reduzir o consumo de energia. Além disso, dois novos algoritmos são propostos para a migração dos roteadores e enlaces virtuais para reduzir o número de roteadores e amplificadores ópticos requeridos. Os resultados obtidos por simulação mostram a eficácia dos algoritmos propostos / Abstract: Network virtualization is a promising technology for the Internet of the Future since it facilitates the deployment of new protocols and applications without the need of changing the core of the network. A key step to instantiate virtual networks is the allocation of physical resources to virtual elements (routers and links). In order to contribute to the global effort of saving energy, choice of physical resources to instantiate a virtual network needs to minimize the network energy consumption. However, this is not a trivial task, since the QoS of the application requirements has to be supported. Indeed, the search for the optimal solution of this problem is NP-hard. The mapping of virtual networks on network substrates at the arrival time of requests to the establishment of virtual networks may not lead to a global minimum energy consumption of energy due to the dynamic allocations and deallocations of virtual networks. Actually, such dynamics can lead to the underutilization of the network substrate. To mitigate the negative effect of this dynamics, techniques such as live migration can be employed to rearrange already mapped virtual networks to achieve energy savings. This dissertation presents a set of new algorithms for the mapping of virtual networks on network substrates aiming to reduce energy consumption. Additionally, two new algorithms are proposed for the migration of virtual routers and links to reduce the number of powered routers and optical amplifiers. Results derived by simulation show the efficacy of the proposed algorithms / Mestrado / Ciência da Computação / Mestre em Ciência da Computação