Computer and Systems Architecture Commons^™

Improving The Performance And Energy Efficiency Of Emerging Memory Systems, Yuhua Guo

Theses and Dissertations

Modern main memory is primarily built using dynamic random access memory (DRAM) chips. As DRAM chip scales to higher density, there are mainly three problems that impede DRAM scalability and performance improvement. First, DRAM refresh overhead grows from negligible to severe, which limits DRAM scalability and causes performance degradation. Second, although memory capacity has increased dramatically in past decade, memory bandwidth has not kept pace with CPU performance scaling, which has led to the memory wall problem. Third, DRAM dissipates considerable power and has been reported to account for as much as 40% of the total system energy and this …

A Framework For Understanding, Prioritizing, And Applying Systems Security Engineering Processes, Activities, And Tasks, Stephen Khou

Theses and Dissertations

Current systems security practices lack an effective approach to prioritize and tailor systems security efforts to develop and field secure systems in challenging operational environments, which results in business and mission stakeholders becoming more susceptible to an array of disruptive events. This work informs Systems Engineers on recent developments in the field of system security engineering and provides a framework for more fully understanding the application of Systems Security Engineering (SSE) processes, activities, and tasks as described in the recently released National Institute of Standards and Technology (NIST) Special Publication 800-160. This SSE framework uniquely offers a repeatable and tailorable …

Development Of The Architecture Cost Effectiveness Framework And Application To Open Systems Architectures, Donald A. Barrett

Theses and Dissertations

The Modular Open System Approach (MOSA) is an initiative to, among other things, reduce cost and schedule for acquisitions programs. While programs have experienced savings using MOSA, the majority of programs have not, in part due to a lack of a logical method for evaluating architecture alternatives. This research develops the Architecture Cost Effectiveness Framework (ACEF), which combines multi-attribute utility analysis with cost effectiveness analysis throughout the program lifecycle. Step 1 is the establishment of a business strategy that includes an Attribute Hierarchy of selected operational requirements. The business strategy also defines Lifecycle Utility Reference Profiles (LURPs) that document changing …

Towards Design And Analysis For High-Performance And Reliable Ssds, Qianbin Xia

Theses and Dissertations

NAND Flash-based Solid State Disks have many attractive technical merits, such as low power consumption, light weight, shock resistance, sustainability of hotter operation regimes, and extraordinarily high performance for random read access, which makes SSDs immensely popular and be widely employed in different types of environments including portable devices, personal computers, large data centers, and distributed data systems.

However, current SSDs still suffer from several critical inherent limitations, such as the inability of in-place-update, asymmetric read and write performance, slow garbage collection processes, limited endurance, and degraded write performance with the adoption of MLC and TLC techniques. To alleviate these …

Improving The Performance And Time-Predictability Of Gpus, Yijie Huangfu

Theses and Dissertations

Graphic Processing Units (GPUs) are originally mainly designed to accelerate graphic applications. Now the capability of GPUs to accelerate applications that can be parallelized into a massive number of threads makes GPUs the ideal accelerator for boosting the performance of such kind of general-purpose applications. Meanwhile it is also very promising to apply GPUs to embedded and real-time applications as well, where high throughput and intensive computation are also needed.

However, due to the different architecture and programming model of GPUs, how to fully utilize the advanced architectural features of GPUs to boost the performance and how to analyze the …

Mitigating Interference During Virtual Machine Live Migration Through Storage Offloading, Morgan S. Stuart

Theses and Dissertations

Today's cloud landscape has evolved computing infrastructure into a dynamic, high utilization, service-oriented paradigm. This shift has enabled the commoditization of large-scale storage and distributed computation, allowing engineers to tackle previously untenable problems without large upfront investment. A key enabler of flexibility in the cloud is the ability to transfer running virtual machines across subnets or even datacenters using live migration. However, live migration can be a costly process, one that has the potential to interfere with other applications not involved with the migration. This work investigates storage interference through experimentation with real-world systems and well-established benchmarks. In order to …

Optimizing Virtual Machine I/O Performance In Cloud Environments, Tao Lu

Theses and Dissertations

Maintaining closeness between data sources and data consumers is crucial for workload I/O performance. In cloud environments, this kind of closeness can be violated by system administrative events and storage architecture barriers. VM migration events are frequent in cloud environments. VM migration changes VM runtime inter-connection or cache contexts, significantly degrading VM I/O performance. Virtualization is the backbone of cloud platforms. I/O virtualization adds additional hops to workload data access path, prolonging I/O latencies. I/O virtualization overheads cap the throughput of high-speed storage devices and imposes high CPU utilizations and energy consumptions to cloud infrastructures. To maintain the closeness between …

A Reused Distance Based Analysis And Optimization For Gpu Cache, Dongwei Wang

Theses and Dissertations

As a throughput-oriented device, Graphics Processing Unit(GPU) has already integrated with cache, which is similar to CPU cores. However, the applications in GPGPU computing exhibit distinct memory access patterns. Normally, the cache, in GPU cores, suffers from threads contention and resources over-utilization, whereas few detailed works excavate the root of this phenomenon. In this work, we adequately analyze the memory accesses from twenty benchmarks based on reuse distance theory and quantify their patterns. Additionally, we discuss the optimization suggestions, and implement a Bypassing Aware(BA) Cache which could intellectually bypass the thrashing-prone candidates.

BA cache is a cost efficient cache design …

Privacy Protection On Cloud Computing, Min Li

Theses and Dissertations

Cloud is becoming the most popular computing infrastructure because it can attract more and more traditional companies due to flexibility and cost-effectiveness. However, privacy concern is the major issue that prevents users from deploying on public clouds. My research focuses on protecting user's privacy in cloud computing. I will present a hardware-based and a migration-based approach to protect user's privacy. The root cause of the privacy problem is current cloud privilege design gives too much power to cloud providers. Once the control virtual machine (installed by cloud providers) is compromised, external adversaries will breach users’ privacy. Malicious cloud administrators are …

Evaluation Of Cyber Sensors For Enhancing Situational Awareness In The Ics Environment, Jeremy R. Otis

Theses and Dissertations

Industrial Control Systems (ICS) monitor and control operations associated with the national critical infrastructure (e.g., electric power grid, oil and gas pipelines and water treatment facilities). These systems rely on technologies and architectures that were designed for system reliability and availability. Security associated with ICS was never an inherent concern, primarily due to the protections afforded by network isolation. However, a trend in ICS operations is to migrate to commercial networks via TCP/IP in order to leverage commodity benefits and cost savings. As a result, system vulnerabilities are now exposed to the online community. Indeed, recent research has demonstrated that …

Characterization And Dynamic Analysis Of Long-Cavity Multi-Section Gain-Levered Quantum-Dot Lasers, John R. Schmidt

Theses and Dissertations

This research investigates the impact of different device architectures on the frequency response of long-cavity multi-section quantum-dot lasers. This work focused on a novel 8.3-mm multi-section quantum-dot device which possessed the flexibility to be configured either as a single- or multi-section device having gain-to-modulation section ratios of 14:2 and 15:1. The long-cavity device design facilitated the testing of increased gain-to-modulation section length ratios previously unexplored in the context of the gain-lever effect. The investigation of the gain-lever effect showed improvements to both the modulation efficiency and modulation bandwidth of the device under test. The modulation efficiency and modulation bandwidth were …

Machine Conscious Architecture For State Exploitation And Decision Making, Mark M. Derriso

Theses and Dissertations

This research addressed a critical limitation in the area of computational intelligence by developing a general purpose architecture for information processing and decision making. Traditional computational intelligence methods are best suited for well-defined problems with extensive, long-term knowledge of the environmental and operational conditions the system will encounter during operation. These traditional approaches typically generate quick answers (i.e., reflexive responses) using pattern recognition methods. Most pattern recognition techniques are static processes which consist of a predefined series of computations. For these pattern recognition approaches to be effective, training data is required from all anticipated environments and operating conditions. The proposed …

Estimating And Measuring Application Latency Of Typical Distributed Interactive Simulation (Dis) - Based Simulation Architecture, Ryan L. Drinkwater

Theses and Dissertations

One of the challenges in a distributed virtual environment stems from the requirement to simultaneously execute the simulations in realtime to support human interaction, in conjunction with maintaining a consistent view of the shared simulated environment. Maintaining a consistent set of simulation state data in the presence of network latency is difficult if individual data items are updated frequently. The principle application of DIS-based simulation environments has been in the domain of training where a consistent view or its correctness is often judged in subjective terms such as the simulation looking and feeling correct. New application areas for these systems …

An Architecture For Coexistence With Multiple Users In Frequency Hopping Cognitive Radio Networks, Ryan K. Mclean

Theses and Dissertations

The radio frequency (RF) spectrum is a limited resource. Spectrum allotment disputes stem from this scarcity as many radio devices are con confined to a fixed frequency or frequency sequence. One alternative is to incorporate cognition within a configurable radio platform, therefore enabling the radio to adapt to dynamic RF spectrum environments. In this way, the radio is able to actively observe the RF spectrum, orient itself to the current RF environment, decide on a mode of operation, and act accordingly, thereby sharing the spectrum and operating in more flexible manner. This research presents a novel framework for incorporating several …

Effects Of Architecture On Information Leakage Of A Hardware Advanced Encryption Standard Implementation, Eric A. Koziel

Theses and Dissertations

Side-channel analysis (SCA) is a threat to many modern cryptosystems. Many countermeasures exist, but are costly to implement and still do not provide complete protection against SCA. A plausible alternative is to design the cryptosystem using architectures that are known to leak little information about the cryptosystem's operations. This research uses several common primitive architectures for the Advanced Encryption Standard (AES) and assesses the susceptibility of the full AES system to side-channel attack for various primitive configurations. A combined encryption/decryption core is also evaluated to determine if variation of high-level architectures affects leakage characteristics. These different configurations are evaluated under …

A Study Of Executable Model Based Systems Engineering From Dodaf Using Simulink, Weston J. Hanoka, Michael H. Ryan

Theses and Dissertations

Diagrams and visuals often cannot adequately capture a complex system’s architecture for analysis. The Department of Defense Architectural Framework (DoDAF), written to follow the Unified Modeling Language (UML), is a collection of mandated common architectural products for interoperability among the DoD components. In this study, DoDAF products from as-is Remotely Piloted Aircraft (RPA) Satellite Communication (SATCOM) systems have been utilized for the creation of executable architectures as part of an Executable Model Based Systems Engineering (EMBSE) process. EMBSE was achieved using Simulink, a software tool for modeling, simulating and analyzing dynamic systems.

This study has demonstrated that DoDAF products can …

A Real-Time Strategy Agent Framework And Strategy Classifier For Computer Generated Forces, Lyall J. Di Trapani

Theses and Dissertations

This research effort is concerned with the advancement of computer generated forces AI for Department of Defense (DoD) military training and education. The vision of this work is agents capable of perceiving and intelligently responding to opponent strategies in real-time. Our research goal is to lay the foundations for such an agent. Six research objectives are defined: 1) Formulate a strategy definition schema effective in defining a range of RTS strategies. 2) Create eight strategy definitions via the schema. 3) Design a real-time agent framework that plays the game according to the given strategy definition. 4) Generate an RTS data …

Twitter Malware Collection System: An Automated Url Extraction And Examination Platform, Benjamin B. Kuhar

Theses and Dissertations

As the world becomes more interconnected through various technological services and methods, the threat of malware is increasingly looming overhead. One avenue in particular that is examined in this research is the social networking service Twitter. This research develops the Twitter Malware Collection System (TMCS). This system gathers Uniform Resource Locators (URLs) posted on Twitter and scans them to determine if any are hosting malware. This scanning process is performed by a cluster of Virtual Machines (VMs) running a specified software configuration and the execution prevention system known as ESCAPE, which detects malicious code. When a URL is detected by …

Host-Based Systemic Network Obfuscation System For Windows, Kevin E. Huber

Theses and Dissertations

Network traffic identifies the operating system and services of the host that created the traffic. Current obfuscation programs focus solely on the Transport and Internet layer protocols of the TCP/IP model. Few obfuscation programs were developed to run on a Windows operating system to provide host-based obfuscation. Systemic Network Obfuscation System (SNOS) was developed to provide a thorough obfuscation process for network traffic on the Windows operating system. SNOS modifies the protocols found at all layers of the TCP/IP model to effectively obfuscate the Windows operating system and services running on the host.

Dynamic Polymorphic Reconfiguration To Effectively “Cloak” A Circuit’S Function, Jeffrey L. Falkinburg

Theses and Dissertations

Today's society has become more dependent on the integrity and protection of digital information used in daily transactions resulting in an ever increasing need for information security. Additionally, the need for faster and more secure cryptographic algorithms to provide this information security has become paramount. Hardware implementations of cryptographic algorithms provide the necessary increase in throughput, but at a cost of leaking critical information. Side Channel Analysis (SCA) attacks allow an attacker to exploit the regular and predictable power signatures leaked by cryptographic functions used in algorithms such as RSA. In this research the focus on a means to counteract …

A Multi Agent System For Flow-Based Intrusion Detection Using Reputation And Evolutionary Computation, David Hancock

Theses and Dissertations

The rising sophistication of cyber threats as well as the improvement of physical computer network properties present increasing challenges to contemporary Intrusion Detection (ID) techniques. To respond to these challenges, a multi agent system (MAS) coupled with flow-based ID techniques may effectively complement traditional ID systems. This paper develops: 1) a scalable software architecture for a new, self-organized, multi agent, flow-based ID system; and 2) a network simulation environment suitable for evaluating implementations of this MAS architecture and for other research purposes. Self-organization is achieved via 1) a reputation system that influences agent mobility in the search for effective vantage …

Adaptive Quality Of Service Engine With Dynamic Queue Control, James D. Haught

Theses and Dissertations

While the current routing and congestion control algorithms in use today are often sufficient for networks with relatively static topology, these algorithms may not be sufficient for military networks where a certain level of quality of service (QoS) needs to be achieved to complete a mission. Current networking technology limits a network's ability to adapt to changes and interactions in the network, often resulting in sub-optimal performance. This research investigates the use of queue size predictions to create a network controller to optimize computer networks. These queue size predictions are made possible through the use of Kalman filters to detect …

Covert Channels Within Irc, Wayne C. Henry

Theses and Dissertations

The exploration of advanced information hiding techniques is important to understand and defend against illicit data extractions over networks. Many techniques have been developed to covertly transmit data over networks, each differing in their capabilities, methods, and levels of complexity. This research introduces a new class of information hiding techniques for use over Internet Relay Chat (IRC), called the Variable Advanced Network IRC Stealth Handler (VANISH) system. Three methods for concealing information are developed under this framework to suit the needs of an attacker. These methods are referred to as the Throughput, Stealth, and Baseline scenarios. Each is designed for …

An Architecture For Improving Timeliness And Relevance Of Cyber Incident Notifications, James L. Miller

Theses and Dissertations

This research proposes a communications architecture to deliver timely and relevant cyber incident notifications to dependent mission stakeholders. This architecture, modeled in Unified Modeling Language (UML), eschews the traditional method of pushing notifications via message as dictated in Air Force Instruction 33-138. It instead shifts to a pull or publish and subscribe method of making notifications. Shifting this paradigm improves the notification process by empowering mission owners to identify those resources on which they depend for mission accomplishment, provides a direct conduit between providing and dependent mission owners for notifications when an incident occurs, and provides a shared representation for …

Defensive Cyber Battle Damage Assessment Through Attack Methodology Modeling, Ryan T. Ostler

Theses and Dissertations

Due to the growing sophisticated capabilities of advanced persistent cyber threats, it is necessary to understand and accurately assess cyber attack damage to digital assets. This thesis proposes a Defensive Cyber Battle Damage Assessment (DCBDA) process which utilizes the comprehensive understanding of all possible cyber attack methodologies captured in a Cyber Attack Methodology Exhaustive List (CAMEL). This research proposes CAMEL to provide detailed knowledge of cyber attack actions, methods, capabilities, forensic evidence and evidence collection methods. This product is modeled as an attack tree called the Cyber Attack Methodology Attack Tree (CAMAT). The proposed DCBDA process uses CAMAT to analyze …

Spear Phishing Attack Detection, David T. Merritt

Theses and Dissertations

This thesis addresses the problem of identifying email spear phishing attacks, which are indicative of cyber espionage. Spear phishing consists of targeted emails sent to entice a victim to open a malicious file attachment or click on a malicious link that leads to a compromise of their computer. Current detection methods fail to detect emails of this kind consistently. The SPEar phishing Attack Detection system (SPEAD) is developed to analyze all incoming emails on a network for the presence of spear phishing attacks. SPEAD analyzes the following file types: Windows Portable Executable and Common Object File Format (PE/COFF), Adobe Reader, …

Trust Management And Security In Satellite Telecommand Processing, Mark C. Duncan

Theses and Dissertations

New standards and initiatives in satellite system architecture are moving the space industry to more open and efficient mission operations. Primarily, these standards allow multiple missions to share standard ground and space based resources to reduce mission development and sustainment costs. With the benefits of these new concepts comes added risk associated with threats to the security of our critical space assets in a contested space and cyberspace domain. As one method to mitigate threats to space missions, this research develops, implements, and tests the Consolidated Trust Management System (CTMS) for satellite flight software. The CTMS architecture was developed using …

Network Security Toolkit Including Heuristic Solutions For Trust System Placement And Network Obfuscation, Gabriel H. Greve

Theses and Dissertations

For Part I, a supervisory control and data acquisition (SCADA) network consists of a group stations and substations in a portion of the power grid. The use of Internet technology in SCADA communications as well as other factors has caused vulnerabilities. One idea to help mitigate this risk is to strategically place trust nodes to compartmentalize and secure the SCADA systems without disturbing its finely honed processes. The trust nodes combine firewall and intrusion detection technology to provide more secure communication. An optimal solution to this problem has already been developed using a mixed-integer linear programming model. Because the problem …

Knowledge-Based Decision Support In Department Of Defense Acquisitions, Clifton L. Hicks

Theses and Dissertations

Despite numerous reform efforts over the past 30 years, acquisition programs in the Department of Defense (DoD) continue to experience cost overruns and schedule delays. One contributing factor is the decision-making process used by defense officials. The General Accounting Office (GAO) has stated that ‘poor program outcomes are the lack of widespread adoption of a knowledge-based acquisition process within DoD despite polices that support such a process. A knowledge-based business case at the outset of each program would alleviate overpromising on cost, schedule, and performance and would empower program managers.’ Effective decision-making for acquisition programs is very important. It not …

A Dynamically Configurable Log-Based Distributed Security Event Detection Methodology Using Simple Event Correlator, Justin M. Myers

Theses and Dissertations

Log event correlation is an effective means of detecting system faults and security breaches encountered in information technology environments. Centralized, database-driven log event correlation is common, but suffers from flaws such as high network bandwidth utilization, significant requirements for system resources, and difficulty in detecting certain suspicious behaviors. This research presents a distributed event correlation system which performs security event detection, and compares it with a centralized alternative. The comparison measures the value in distributed event correlation by considering network bandwidth utilization, detection capability and database query efficiency, as well as through the implementation of remote configuration scripts and correlation …