Seismic tomography is a technique for illuminating the physical dynamics of the Earth by seismic waves generated by earthquakes or explosions. In both industry and academia, the seismic exploration does not yet have the capability of imaging seismic tomography in real-time and with high resolution. There are two reasons. First, at present raw seismic data are typically recorded on sensor nodes locally then are manually collected to central observatories for post processing, and this process may take months to complete. Second, high resolution tomography requires a large and dense sensor network, the real-time data retrieval from a network of large-amount wireless seismic nodes to a central server is virtually impossible due to the sheer data amount and resource limitations. This limits our ability to understand earthquake zone or volcano dynamics. To obtain the seismic tomography in real-time and high resolution, a new design of sensor network system for raw seismic data processing and distributed tomography computation is demanded. Based on these requirements, three research aspects are addressed in this work. First, a distributed multi-resolution evolving tomography computation algorithm is proposed to compute tomography in the network, while avoiding costly data collections and centralized computations. Second, InsightTomo, an end-to-end sensor network emulation platform, is designed to emulate the entire process from data recording to tomography image result delivery. Third, a sensor network testbed is presented to verify the related methods and design in real world. The design of the platform consists of hardware, sensing and data processing components.

Network processors are becoming a predominant feature in the field of network hardware. As new network protocols emerge and data speeds increase, contemporary general-purpose network processors are entering their second generation and academic research is being actively conducted into new techniques for the design and implementation of these systems. At the same time, systems ranging from secured military communications equipment to consumer devices are being updated to provide network connectivity. Many of these devices require, or would benefit from, the inclusion of device security in addition to data security. Whether it is a top-secret encryption scheme that must be concealed or a personal device that needs protection against unauthorized use, security of the device itself is becoming an important factor in system design. Unfortunately, current network processor solutions were not developed with device security in mind. A secure adaptive network processor can provide the means to fill this gap while continuing to provide full support for emerging communication protocols. This dissertation describes the concept and structure of one such device. Analysis of the hardware security provided by the proposed device is provided to highlight strengths and weaknesses, while a prototype system is developed to allow it to be embedded into practical applications for investigation. Two such applications are developed, using the device to provide support for both a secure network edge device and a user-adaptable network gateway. Results of these experiments indicate that the proposed device is useful both as a hardware security measure and as a basis for user adaptation of information-handling systems. / Ph. D.

Wireless sensor networks (WSNs) allow us to instrument the physical world in novel ways, providing detailed insight that has not been possible hitherto. Since WSNs provide an interface to the physical world, each sensor node has a location in physical space, thereby enabling us to associate spatial properties with data. Since WSNs can perform periodic sensing tasks, we can also associate temporal markers with data. In the environmental sciences, in particular, WSNs are on the way to becoming an important tool for the modelling of spatially and temporally extended physical phenomena. However, support for high-level and expressive spatial-analytic tasks that can be executed inside WSNs is still incipient. By spatial analysis we mean the ability to explore relationships between spatially-referenced entities (e.g., a vineyard, or a weather front) and to derive representations grounded on such relationships (e.g., the geometrical extent of that part of a vineyard that is covered by mist as the intersection of the geometries that characterize the vineyard and the weather front, respectively). The motivation for this endeavour stems primarily from applications where important decisions hinge on the detection of an event of interest (e.g., the presence, and spatio-temporal progression, of mist over a cultivated field may trigger a particular action) that can be characterized by an event-defining predicate (e.g., humidity greater than 98 and temperature less than 10). At present, in-network spatial analysis in WSN is not catered for by a comprehensive, expressive, well-founded framework. While there has been work on WSN event boundary detection and, in particular, on detecting topological change of WSN-represented spatial entities, this work has tended to be comparatively narrow in scope and aims. The contributions made in this research are constrained to WSNs where every node is tethered to one location in physical space. The research contributions reported here include (a) the definition of a framework for representing geometries; (b) the detailed characterization of an algebra of spatial operators closely inspired, in its scope and structure, by the Schneider-Guting ROSE algebra (i.e., one that is based on a discrete underlying geometry) over the geometries representable by the framework above; (c) distributed in-network algorithms for the operations in the spatial algebra over the representable geometries, thereby enabling (i) new geometries to be derived from induced and asserted ones, and (ii)topological relationships between geometries to be identified; (d) an algorithmic strategy for the evaluation of complex algebraic expressions that is divided into logically-cohesive components; (e) the development of a task processing system that each node is equipped with, thereby with allowing users to evaluate tasks on nodes; and (f) an empirical performance study of the resulting system.

Seven to ten percent of the energy used globally goes towards powering information and communications technology (ICT): the global data- and telecommunications network, the private and commercial datacenters it supports, and the 19 billion electronic devices around the globe it interconnects, through which we communicate, and access and produce information. As bandwidth and data rates increase, so does the volume of traffic, as well as the absolute amount of new information digitized and uploaded onto the Net and into the cloud each second. Words like gigabit and terabyte were needless fifteen years ago in the public arena; now, they are common phrases. As people use their networked devices to do more, to access more, to send more, and to connect more, they use more energy--not only in their own devices, but also throughout the ICT. While there are many endeavors focused on individual low-power devices, few are examining broad strategies that cross the many boundaries of separate concerns within the ICT; also, few are assessing the impact of specific strategies on the global energy supply: at a global scale. This work examines the energy savings of several such strategies; it also assesses their efficacy in reducing energy consumption, both within specific networks and within the larger ICT. All of these strategies save energy by reducing the work done by the system as a whole on behalf of a single user, often by exploiting commonalities among what many users around the globe are also doing to amortize the costs. / Ph. D.

Master of Science / Department of Computing and Information Sciences / Gurdip Singh / Severe energy constraints and limited computing abilities of the nodes in a network present a major challenge in the design and deployment of a wireless sensor network. This thesis aims to present energy efficient algorithms for data fusion and information aggregation in a sensor network. The various methodologies of data fusion presented in this thesis intend to reduce the data traffic within a network by mapping the sensor network application task graph onto a sensor network topology. Partitioning of an application into sub-tasks that can be mapped onto the nodes of a sensor network offers opportunities to reduce the overall energy consumption of a sensor network. The first approach proposes a grid based coordinated incremental data fusion and routing with heterogeneous nodes of varied computational abilities. In this approach high performance nodes arranged in a mesh like structure spanning the network topology, are present amongst the resource constrained nodes. The sensor network protocol performance, measured in terms of hop-count is analysed for various grid sizes of the high performance nodes. To reduce network traffic and increase the energy efficiency in a randomly deployed sensor network, distributed clustering strategies which consider network density and structure similarity are applied on the network topology. The clustering methods aim to improve the energy efficiency of the sensor network by dividing the network into logical clusters and mapping the fusion points onto the clusters. Routing of network information is performed by inter-cluster and intra-cluster routing.

Networking technology is connecting more and more people around the world. It has become an essential part of our daily life. For this connectivity to be seamless, networks need to be fast. Nonetheless, rapid growth in network traffic and variety of communication protocols overwhelms the Central Processing Units (CPUs) processing packets in the networks. Existing solutions to this problem such as ASIC, FPGA, NPU, and TOE are not cost effective and easy to manage because they require special hardware and custom configurations. This thesis approaches the problem differently by offloading the network processing to off-the-shelf Graphic Processing Units (GPUs). The thesis's primary goal is to find out how the GPUs should be used for the offloading. The thesis follows the case study approach and the selected case studies are layer 2 Bloom filter forwarding and flow lookup in Openflow switch. Implementation alternatives and evaluation methodology are proposed for both of the case studies. Then, the prototype implementation for comparing between traditional CPU-only and GPU-offloading approach is developed and evaluated. The primary findings from this work are criteria of network processing functions suitable for GPU offloading and tradeoffs involved. The criteria are no inter-packet dependency, similar processing flows for all packets, and within-packet parallel processing opportunity. This offloading trades higher latency and memory consumption for higher throughput. / Nätverksteknik ansluter fler och fler människor runt om i världen. Det har blivit en viktig del av vårt dagliga liv. För att denna anslutning skall vara sömlös, måste nätet vara snabbt. Den snabba tillväxten i nätverkstrafiken och olika kommunikationsprotokoll sätter stora krav på processorer som hanterar all trafik. Befintliga lösningar på detta problem, t.ex. ASIC, FPGA, NPU, och TOE är varken kostnadseffektivt eller lätta att hantera, eftersom de kräver speciell hårdvara och anpassade konfigurationer. Denna avhandling angriper problemet på ett annat sätt genom att avlasta nätverks processningen till grafikprocessorer som sitter i vanliga pc-grafikkort. Avhandlingen främsta mål är att ta reda på hur GPU bör användas för detta. Avhandlingen följer fallstudie modell och de valda fallen är lager 2 Bloom filter forwardering och ``flow lookup'' i Openflow switch. Implementerings alternativ och utvärderingsmetodik föreslås för både fallstudierna. Sedan utvecklas och utvärderas en prototyp för att jämföra mellan traditionell CPU- och GPU-offload. Det primära resultatet från detta arbete utgör kriterier för nätvärksprocessfunktioner lämpade för GPU offload och vilka kompromisser som måste göras. Kriterier är inget inter-paket beroende, liknande processflöde för alla paket. och möjlighet att köra fler processer på ett paket paralellt. GPU offloading ger ökad fördröjning och minneskonsumption till förmån för högre troughput.

No description available.