No description available.

The ever-increasing applications of Big Data in improving networking application performancehave motivated the networking community to deploy it in SDN (Software defined network) toconstruct flexible, scalable, self-aware, and self-managing networks. The primary purpose ofthis research is to investigate the validity of tensor-decomposition, a well-knownmathematical approach for data reduction, to catch patterns in network traffic as an initialstep toward the network's intelligence.Using only three-dimensional (cubic) tensors (Source, Destination, Bandwidth). Theconducted research used both offline (not simulated) and online (Mininet and RYU controllersimulation) network traffic of the GEANT (TOTEM) dataset. From the tensor decompositionanalysis on the adjacency matricies, we caught traffic intensity patterns between nodes(switches), which provided suggestions that helps rebuild the topology (which nodes shouldbe physically connected to the others). However, capturing the patterns in the time revolutionwas invalid due to limitations in the three-dimensional tensor.

While the toolset known as Machine Learning (ML) is not new, several of the tools available within the toolset have seen revitalization with improved hardware, and have been applied across several domains in the last two decades. Deep Neural Network (DNN) applications have contributed to significant research within Radio Frequency (RF) problems over the last decade, spurred by results in image and audio processing. Machine Learning (ML), and Deep Learning (DL) specifically, are driven by access to relevant data during the training phase of the application due to the learned feature sets that are derived from vast amounts of similar data. Despite this critical reliance on data, the literature provides insufficient answers on how to quantify the data training needs of an application in order to achieve a desired performance. This dissertation first aims to create a practical definition that bounds the problem space of Radio Frequency Machine Learning (RFML), which we take to mean the application of Machine Learning (ML) as close to the sampled baseband signal directly after digitization as is possible, while allowing for preprocessing when reasonably defined and justified. After constraining the problem to the Radio Frequency Machine Learning (RFML) domain space, an understanding of what kinds of Machine Learning (ML) have been applied as well as the techniques that have shown benefits will be reviewed from the literature. With the problem space defined and the trends in the literature examined, the next goal aims at providing a better understanding for the concept of data quality through quantification. This quantification helps explain how the quality of data: affects Machine Learning (ML) systems with regard to final performance, drives required data observation quantity within that space, and impacts can be generalized and contrasted. With the understanding of how data quality and quantity can affect the performance of a system in the Radio Frequency Machine Learning (RFML) space, an examination of the data generation techniques and realizations from conceptual through real-time hardware implementations are discussed. Consequently, the results of this dissertation provide a foundation for estimating the investment required to realize a performance goal within a Deep Learning (DL) framework as well as a rough order of magnitude for common goals within the Radio Frequency Machine Learning (RFML) problem space. / Doctor of Philosophy / Machine Learning (ML) is a powerful toolset capable of solving difficult problems across many domains. A fundamental part of this toolset is the representative data used to train a system. Unlike the domains of image or audio processing, for which datasets are constantly being developed thanks to usage agreements with entities such as Facebook, Google, and Amazon, the field of Machine Learning (ML) within the Radio Frequency (RF) domain, or Radio Frequency Machine Learning (RFML), does not have access to such crowdsourcing means of creating labeled datasets. Therefore data within the Radio Frequency Machine Learning (RFML) problem space must be intentionally cultivated to address the target problem. This dissertation explains the problem space of Radio Frequency Machine Learning (RFML) and then quantifies the effect of quality on data used during the training of Radio Frequency Machine Learning (RFML) systems. Taking this one step further, the work then goes on to provide a means of estimating data quantity needs to achieve high levels of performance based on the current Deep Learning (DL) approach to solve the problem, which in turn can be used as guidance to better refine the approach when the real-world data quantity requirements exceed practical acquisition levels. Finally, the problem of data generation is examined and provides context for the difficulties associated with procuring high quality data for problems in the Radio Frequency Machine Learning (RFML) space.

This dissertation provides theory and analysis on the impact resource management has on software-defined radio platforms by investigating the inherent trade-off between spectrum and processing effciencies with their relation to both the power consumed by the host processor and the complexity of the algorithm which it can support. The analysis demonstrates that considerable resource savings can be gained without compromising the resulting quality of service to the user, concentrating specifically on physical-layer signal processing elements commonly found in software definitions of single- and multi-carrier communications signals. Novel synchronization techniques and estimators for unknown physical layer reference parameters are introduced which complement the energy-quality scalability of software-defined receivers. A new framing structure is proposed for single-carrier systems which enables fast synchronization of short packet bursts, applicable for use in dynamic spectrum access. The frame is embedded with information describing its own structure, permitting the receiver to automatically modify its software configuration, promoting full waveformfl‚exibility for adapting to quickly changing wireless channels. The synchronizer's acquisition time is reduced by exploiting cyclostationary properties in the preamble of transmitted framing structure, and the results are validated over the air in a wireless multi-path laboratory environment. Multi-carrier analysis is concentrated on synchronizing orthogonal frequency-division multiplexing (OFDM) using offset quadrature amplitude modulation (OFDM/OQAM) which is shown to have significant spectral compactness advantages over traditional OFDM. Demodulation of OFDM/OQAM is accomplished using computationally effcient polyphase analysis filterbanks, enabled by a novel approximate square-root Nyquist filter design based on the near-optimum Kaiser-Bessel window. Furthermore, recovery of sample timing and carrier frequency offsets are shown to be possible entirely in the frequency domain, enabling demodulation in the presence of strong interference signals while promoting heterogeneous signal coexistence in dynamic spectrum environments. Resource management is accomplished through the introduction of a self-monitoring framework which permits system-level feedback to the radio at run time. The architecture permits the radio to monitor its own processor usage, demonstrating considerable savings in computation bandwidths on the tested platform. Resource management is assisted by supervised intelligent heuristic-based learning algorithms which use software-level feedback of the radio's active resource consumption to optimize energy and processing effciencies in dynamic spectrum environments. In particular, a case database-enabled cognitive engine is proposed which abstracts from the radio application by using specific knowledge of previous experience rather than relying on general knowledge within a specific problem domain. / Ph. D.

In this paper we address radar-communication coexistence by modelling the radar environment as a Markov Decision Process (MDP), and then apply Deep-Q Learning to optimize radar performance. The radar environment includes a single point target and a communications system that will potentially interfere with the radar. We demonstrate that the Deep-Q Network (DQN) we construct is able to successfully avoid interfering with the communication system to improve its performance. We also show that the DQN method outperforms previous methods in terms of memory and handling new situations. In this thesis we also address the application of the MDP into a software defined radio (SDR) USRP X310 by utilizing the software LabVIEW to communicate with and control the SDR. / Master of Science / In this thesis we develop methods for creating and implementing algorithms for a cognitive radar. A cognitive radar is a radar that is able to sense its environment and avoid any other communication system that may interfere with its operation. We discuss the predictive methods we used to sense and avoid the other communication systems as well as how we implemented this using a software defined radar based on the USRP X310.

Software-defined radios have the agility and flexibility to tune performance parameters, allowing them to adapt to environmental changes, adapt to desired modes of operation, and provide varied functionality as needed.  Traditional software-defined radios use a combination of conditional processing and software-tuned hardware to enable these features and will critically sample the spectrum to ensure that only the required bandwidth is digitized.  While flexible, these systems are still constrained to perform only a single function at a time and digitize a single frequency sub-band at time, possibly limiting the radio's effectiveness. Radio systems commonly tune hardware manually or use software controls to digitize sub-bands as needed, critically sampling those sub-bands according to the Nyquist criterion.  Recent technology advancements have enabled efficient and cost-effective over-sampling of the spectrum, allowing all bandwidths of interest to be captured for processing simultaneously, a process known as band-sampling.  Simultaneous access to measurements from all of the frequency sub-bands enables both awareness of the spectrum and seamless operation between radio applications, which is critical to many applications.  Further, more information may be obtained for the spectral content of each sub-band from measurements of other sub-bands that could improve performance in applications such as detecting the presence of interference in weak signal measurements. This thesis presents a new method for confirming the source of detected energy in weak signal measurements by sampling them directly, then estimating their expected effects.  First, we assume that the detected signal is located within the frequency band as measured, and then we assume that the detected signal is, in fact, interference perceived as a result of signal aliasing.  By comparing the expected effects to the entire measurement and assuming the power spectral density of the digitized bandwidth is sparse, we demonstrate the capability to identify the true source of the detected energy.  We also demonstrate the ability of the method to identify interfering signals not by explicitly sampling them, but rather by measuring the signal aliases that they produce.  Finally, we demonstrate that by leveraging techniques developed in the field of Compressed Sensing, the method can recover signal aliases by analyzing less than 25 percent of the total spectrum. / Master of Science

Spectrum sharing is possible, but lacks R & D support for practical solutions that satisfy both the incumbent and secondary or opportunistic users. The author found a lack of an openly available framework supporting experimental research on the performance of a Spectrum Access System (SAS) and propose to build an open-source Software Defined Radio (SDR) based framework. This framework will test different dynamic spectrum scenarios in a wireless testbed. This thesis presents our Spectrum Access System prototype, discusses the design choices and trade-offs and provides a proof of concept implementation. We show that an Internet-accessible CORNET test bed provides the ideal platform for developing and testing the SAS functionality and its building blocks and offerss the hardware and software as a community resource for research and education. This design provides the necessary interfaces for researchers to develop and test their SAS-related modules, waveforms and scenarios. / Master of Science / In this information age, the number of wireless devices is growing faster than the infrastructure required to make wireless communication possible. This creates a possibility of not having enough radio spectrum to keep up with this growing demand. To alleviate this issue, there is a need to research and find more ways of efficiently utilizing the current spectrum resources available. Dynamic spectrum allocation is one way forward to archiving this goal. Frequency channels are assigned to devices based on prevailing conditions like device location and availability of channels that would cause low interference to other devices. Spectrum utilization is based on time, frequency and space with devices having the ability to hop to the best channel available. In this thesis, an open-source Spectrum Access System (SAS) was created as a platform through which dynamic spectrum allocation research can be done. The SAS is centralized management system that logs information about the prevailing spectrum usage, and in turn uses this information to dynamically allocate spectrum to devices and networks. This thesis shows how it was implemented, its current performance, and the steps that different researchers can take to add their own functionalities.

Software-Defined Radio (SDR) is a large field of research, and is rapidly expanding in terms of capabilities and applications. As the number of SDR platforms, deployments, and use-cases grow, interoperability, compatibility, and software re-use becomes more difficult. Additionally, advanced SDR applications require more advanced hardware and software platforms to support them, necessitating intelligent management of resources and functionality. Realizing these goals can be done using the paradigms of Component-Based Design (CBD) and Service-Oriented Architectures (SOAs). Component-based design has been applied to the field of SDR in the past to varying levels of success. We discuss the benefits of CBD, and how to successfully use CBD for SDR. We assert that by strictly enforcing the principles of CBD, we can achieve a high level of independence from both the hardware and software platforms, and enable component compatibility and interoperability between SDR platforms and deployments. Using CBD, we also achieve the use-case of a fully distributed SDR, where multiple hardware nodes act as one cohesive radio unit. Applying the concept of service-orientation to SDR is a novel idea, and we discuss how this enables a new radio paradigm in the form of goal-oriented autonomic radios. We define SOAs in the context of SDR, explain how our vision is different than middle-wares like CORBA, describe how SOAs can be used, and discuss the possibilities of autonomic radio systems. This thesis also presents our work on the Cognitive Radio Open Source Systems (CROSS) project. CROSS is a free and open-source prototype architecture that uses CBD to achieve platform independence and distributed SDR deployments. CROSS also provides an experimental system for using SOAs in SDRs. Using our reference implementation of CROSS, we successfully demonstrated a distributed cognitive radio performing dynamic spectrum access to communicate with another SDR while avoiding an interferer operating in the spectrum. / Master of Science

Modern devices provide a multitude of services that use radio frequencies in continual smaller packages. This size leads to an antenna used to transmit and receive information being usually very inefficient and a lot of power is wasted just to be able to transmit a signal. To mitigate this problem a new antenna was introduced by Dr. Manteghi that is capable of working efficiently across a large band. The antenna achieves this large band by doing quick frequency hopping across multiple channels. In order to test the performance of this antenna against more common antennas, a software radio was needed, such that tested antennas can be analyzed using multiple modulations. This paper presents a software defined radio system that was designed for the purpose of testing the bit-error rate of digital modulations schemes using described and other antennas. The designed system consists of a DSP, an FPGA, and commercially available modules. The combination allows the system to be flexible with high performance, while being affordable. Commercial modules are available for multiple frequency bands and capable of fast frequency switching required to test the antenna. The DSP board contains additional peripherals that allows for more complex projects in the future. The block structure of the system is also very educational as each stage of transmission and reception can be tested and observed. The full system has been constructed and tested using simulated and real signals. A code was developed for communication between commercial modules and the DSP, bit error rate testing, data transmission, signal generation, and signal reception. A graphical user interface (GUI) was developed to help user with information display and system control. This thesis describes the software-defined-radio design in detail and shows test results at the end. / Master of Science

Increasing interest in ultra-wideband (UWB) communications has engendered the need for a test bed for UWB systems. An FPGA-based software-defined radio provides both post-fabrication definition of the radio and ample parallel processing power. This thesis presents the FPGA design for a software-defined radio targeted to impulse ultra-wideband signals. The system is capable of an effective sampling frequency of up to 8 G-samples/s using time interleaved sampling with eight 1-GHz ADCs. The system is also capable of transmitting UWB pulses using a transmitter board controlled by the FPGA. In this thesis, the FPGA design used to capture and export data from the eight ADCs is presented, along with two systems which make use of the transceiver: a pilot-based matched filter communications system, and a remote vital signs monitor. / Master of Science