Improving resource management in virtualized data centers using application performance models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity.^ We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. ^ This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.^

Characterization of Atlantic Cod Spawning Habitat and Behavior in Icelandic Coastal Waters

The physical habitat used during spawning may potentially be an important factor affecting reproductive output of broadcast spawning marine fishes, particularly for species with complex, substrate-oriented mating systems and behaviors, such as Atlantic cod Gadus morhua. We characterized the habitat use and behavior of spawning Atlantic cod at two locations off the coast of southwestern Iceland during a 2-d research cruise (15–16 April 2009). We simultaneously operated two different active hydroacoustic gear types, a split beam echosounder and a dual frequency imaging sonar (DIDSON), as well as a remotely operated underwater vehicle (ROV). A total of five fish species were identified through ROV surveys: including cusk Brosme brosme, Atlantic cod, haddock Melanogrammus aeglefinus, lemon sole Microstomus kitt, and Atlantic redfish Sebastes spp. Of the three habitats identified in the acoustic surveys, the transitional habitat between boulder/lava field and sand habitats was characterized by greater fish density and acoustic target strength compared to that of sand or boulder/lava field habitats independently. Atlantic cod were observed behaving in a manner consistent with published descriptions of spawning. Individuals were observed ascending 1–5 m into the water column from the bottom at an average vertical swimming speed of 0.20–0.25 m s−1 and maintained an average spacing of 1.0–1.4 m between individuals. Our results suggest that cod do not choose spawning locations indiscriminately despite the fact that it is a broadcast spawning fish with planktonic eggs that are released well above the seafloor.

Cognitive performance and the thymus among HIV-infected subjects receiving HAART

Objective: To evaluate the impact of alcohol use, which is widespread in human immunodeficiency virus (HIV)+ individuals, on highly active antiretroviral therapy (HAART)-associated immune and cognitive improvements and the relationship between those two responses. Methods: In a case-control longitudinal study, thymic volume, cognition, and immune responses were evaluated at baseline and after 6 months therapy in HIV+ and HIV- controls. Cognitive performance was evaluated using the HIV Dementia Score (HDS) and the California Verbal Learning Test (CVLT). Results: Prior to HAART, thymic volume varied considerably from 2.7 to 29.3 cm3 (11 ± 7.2 cm3). Thymic volume at baseline showed a significantly inverse correlation with the patient’s number of years of drinking (r2 = 0.207; p < 0.01), as well as HDS and the CVLT scores in both HIV-infected (r2 = 0.37, p = 0.03) and noninfected (r2 = 0.8, p = 0.01). HIV-infected individuals with a small thymic volume scored in the demented range, as compared with those with a larger thymus (7 ± 2.7 vs. 12 ± 2.3, p = 0.005). After HAART, light/moderate drinkers exhibited thymus size twice that of heavy drinkers (14.8 ± 10.4 vs. 6.9 ± 3.3 cm3). Conclusions: HAART-associated increases of thymus volume appear to be negatively affected by alcohol consumption and significantly related to their cognitive status. This result could have important clinical implications.

Effective Reconfigurable Antenna Designs to Enhance Performance and Enable Wireless Powering

With the increase in traffic on the internet, there is a greater demand for wireless mobile and ubiquitous applications. These applications need antennas that are not only broadband, but can also work in different frequency spectrums. Even though there is a greater demand for such applications, it is still imperative to conserve power. Thus, there is a need to design multi-broadband antennas that do not use a lot of power. Reconfigurable antennas can work in different frequency spectrums as well as conserve power. The current designs of reconfigurable antennas work only in one band. There is a need to design reconfigurable antennas that work in different frequency spectrums. In this current era of high power consumption there is also a greater demand for wireless powering. This dissertation explores ideal designs of reconfigurable antennas that can improve performance and enable wireless powering. This dissertation also presents lab results of the multi-broadband reconfigurable antenna that was created. A detailed mathematical analyses, as well as extensive simulation results are also presented. The novel reconfigurable antenna designs can be extended to Multiple Input Multiple Output (MIMO) environments and military applications.

The Relation Between Civic Education and Political Attitudes and Behavior

It is generally assumed that civic education efforts will have a positive effect on the political attitudes and behaviors of adolescents and young adults. There is less agreement, however, on the most effective forms of civic education. In the present study, we distinguish between formal civic education, an open classroom climate and active learning strategies, and we explore their effect on political interest, efficacy, trust and participation. To analyze these effects, we rely on the results of a two-year panel study among late adolescents in Belgium. The results indicate that formal civic education (classroom instruction) and active learning strategies (school council membership and, to a lesser extent, group projects) are effective in shaping political attitudes and behavior. An open classroom climate, on the other hand, has an effect on political trust. We conclude that there is no reason to privilege specific forms of civic education, as each form contributes to different relevant political attitudes and behaviors.

Effects of engine cooling water temperature on performance and emission characteristics of a CI engine operated with biofuel blend

The temperature of the coolant is known to have significant influence on engine performance and emissions. Whereas existing literature describes the effects of coolant temperature in engines using fossil derived fuels, very few studies have investigated these effects when biofuel is used. In this study, Jatropha oil was blended separately with ethanol and butanol. It was found that the 80% jatropha oil + 20% butanol blend was the most suitable alternative, as its properties were closest to that of fossil diesel. The coolant temperature was varied between 50°C and 95°C. The combustion process enhanced for both diesel and biofuel blend, when the coolant temperature was increased. The carbon dioxide emissions for both diesel and biofuel blend were observed to increase with temperature. The carbon monoxide, oxygen and lambda values were observed to decrease with temperature. When the engine was operated using diesel, nitrogen oxides emissions correlated in an opposite manner to smoke opacity; however, nitrogen oxides emissions and smoke opacity correlated in an identical manner for biofuel blend. Brake specific fuel consumption was observed to decrease as the temperature was increased and was higher on average when the biofuel was used. The study concludes that both biofuel blend and fossil diesel produced identical correlations between coolant temperature and engine performance. The trends of nitrogen oxides and smoke emissions with cooling temperatures were not identical to fossil diesel when biofuel blend was used in the engine.

Performance and prospects of smaller UK regional airports

This paper investigates the traffic and financial performance of smaller UK regional airports between 2001 and 2014. Fourteen airports that typically serve less than 5 million passengers per annum were selected for the analysis. A period of strong growth in passenger demand was experienced from 2001 to 2007, driven largely by low cost carriers. The period from 2007 to 2014 was characterised by declining demand, resulting in significant losses for many of the airports. Airline strategies, such as the use of an increased unit fleet size and average sector length, may further limit future prospects for smaller UK regional airports in favour of larger ones with greater local demand. The relationship between traffic throughput and the generation of aeronautical revenues seems to vary at airports. There is generally a strong and significant relationship between traffic throughput and the generation of commercial revenues and total operating costs at airports serving 3–5 million passengers, but the situation for airports serving fewer than 3 million is less certain.

Predicting Student Performance and Differences in Learning Styles based on Textual Complexity Indices applied on Blog and Microblog Posts

Social media tools are increasingly popular in Computer Supported Collaborative Learning and the analysis of students' contributions on these tools is an emerging research direction. Previous studies have mainly focused on examining quantitative behavior indicators on social media tools. In contrast, the approach proposed in this paper relies on the actual content analysis of each student's contributions in a learning environment. More specifically, in this study, textual complexity analysis is applied to investigate how student's writing style on social media tools can be used to predict their academic performance and their learning style. Multiple textual complexity indices are used for analyzing the blog and microblog posts of 27 students engaged in a project-based learning activity. The preliminary results of this pilot study are encouraging, with several indexes predictive of student grades and/or learning styles.

Highway Performance and Time-Sensitive Industries, 1998

This report addresses delays to freight shippers. Although the focus is on just-in-time (JIT) businesses, the authors also note that non JIT businesses also suffer delays that impact their productivity. The table of contents lists the following headings: chapter 1 - introduction - a trial application: the Des Moines metropolitan area; structure of the report; chapter 2 - reliability at the forefront of freight transport demand - manufacturing and inventory; just-in-time operations in the U.S.; transportation consequences; summary; chapter 3 - JIT operations in Iowa - survey and sample; trucking activity and service; just-in-time truck transportation in Iowa; assessment of factors affecting truck transportation service; summary and conclusions; chapter 4 - travel time uncertainty induced by incidents - a probabilistic model for incident occurrences and durations; calculation of delay; trial application; conclusions; and chapter 5 - conclusions and recommendations - conclusions; recommendations.

Only Time Will Tell: The Changing Relationships between LMX, Job Performance, and Justice

Although it has been argued that LMX is a phenomenon that develops over time, the existing LMX literature is largely cross-sectional in nature. Yet, there is a great need for unraveling how LMX develops over time. To address this issue in the LMX literature, we examine the relationships of LMX with two variables known for changing over time: job performance and justice perceptions. On the basis of current empirical findings, a simulation deductively shows that LMX develops over time, but differently in early stages versus more mature stages. Our findings also indicate that performance and justice trends affect LMX. Implications for LMX theory, and for longitudinal research on LMX, performance, and justice are discussed.

A pilot study on the productivity and behavior of the gestating sow housed in a flex stall

Animal welfare is a controversial topic in modern animal agriculture, partly because it generates interest from both the scientific community and the general public. The housing of gestating sows, particularly individual housing, is one of the most critical concerns in farm animal welfare. We hypothesize that the physical size of the standard gestation stall may limit movement and evoke demands and challenges on the sow to affect the physiological and psychological well-being of the individually housed sow. Thus, improvements in the design of the individual gestation stall system that allow more freedom to move, such as increasing stall width or designing a stall that could accommodate the changing size of the pregnant sow, may improve sow welfare. The objective of this pilot study was to evaluate the effects of a width adjustable stall (FLEX) on productivity and behavior of dry sows. The experiment consisted of 3 replications (block 1, n=4 sows; block 2, n=4 sows; block 3, n=8 sows), and multi-parious sows were allotted to either a FLEX stall or standard gestation stall for 1 gestation period. Sow mid-girth (top of the back to bottom of the udder) was measured 5-6 times throughout gestation to determine the best time points for FLEX stall width expansions. FLEX stall width was adjusted according to mid-girth measurements, and expanded to achieve an additional 2 cm of space between the bottom of the sow’s udder and floor of the stall so that sows could lie in full lateral recumbency without touching the sides of the stall. Productivity data recorded included: sow body weight (BW) and BW gain, number of piglets born and born alive, proportions of piglets stillborn, mummified, lost between birth and weaning, and weaned, and litter and mean piglet birth BW, weaning BW, and average BW gain from birth-to-weaning. Lesions were recorded on d 21 and d 111 of gestation. Sub-pilot behavior data were observed and registered for replicate 1 sows using continuous video-records for the l2 hour lights on period (period 1, 0600-1000; period 2, 1000-1400; period 3, 1400-1800) prior FLEX stall adjustment and 12 hour lights on period post adjustment on d 21, 22, 23, 43, 44, 45, 93, 94, 95. A randomized complete block design with a 2 × 2 factorial arrangement for treatments was used to analyze sow productivity and performance traits. Data were analyzed using the Mixed Models procedure of SAS. A preliminary analysis of data means and numerical trends was used to analyze sow behavior measurements. Sows housed in a FLEX stall had more (P < 0.05) total born and a tendency for more piglets born alive (P = 0.06) than sows housed in a standard stall. Sow body weight also tended to be higher (P = 0.06) for sows housed in a FLEX stall compared to sows housed in a standard stall. There were numerical trends for mean durations of sit, lay, lay (OUT), and eat behaviors to be greater for sows housed in a FLEX stall compared with sows housed in a standard stall. The mean duration of lay (IN) behavior tended to be numerically less for sows housed in a FLEX stall compared with sows housed in a standard stall. There were numerical trends for the mean durations of stand and drink behaviors to be greater for sows housed in a standard stall compared with sows housed in a FLEX stall. The mean frequencies of postural changes and mean durations of oral-nasal-facial and sham-chew behaviors were numerically similar between types of gestation stall. Mean durations and numerical trends indicate that time of day influenced all of the behaviors assessed in this study. The results of this pilot study indicate that the adjustable FLEX stall may affect sow productivity and behavior differently than the standard gestation stall, and thus potentially improve sow well-being. Future research should continue to compare the new FLEX stall design to current housing systems in use and examine physiological traits and immune status in addition to behavioral and productivity traits to assess the effects that this housing system has on the overall welfare of the gestating sow.

Too Busy to Be Fair? The Effect of Managers’ Perceived Workload on Their Core Technical Performance and Justice Rule Adherence

Despite the organizational benefits of treating employees fairly, both anecdotal and empirical evidence suggest that managers do not behave fairly towards their employees in a consistent manner. As treating employees fairly takes up personal resources such as time, effort, and attention, I argue that when managers face high workloads (i.e., high amounts of work and time pressure), they are unable to devote such personal resources to effectively meet both core technical task requirements and treat employees fairly. I propose that in general, managers tend to view their core technical task performance as more important than being fair in their dealings with employees; as a result, when faced with high workloads, they tend to prioritize the former at the expense of the latter. I also propose that managerial fairness will suffer more as a result of heightened workloads than will core technical task performance, unless managers perceive their organization to explicitly reward fair treatment of employees. I find support for my hypotheses across three studies: two experimental studies (with online participants and students respectively) and one field study of managers from a variety of organizations. I discuss the implications of studying fairness in the wider context of managers’ complex role in organizations to the fairness and managerial work demands literatures.

MULTIMODAL PERFORMANCE AND RELIABILITY ANALYSIS OF THE PIERRE AUGER OBSERVATORY NORTH SITE

The Pierre Auger Cosmic Ray Observatory North site employs a large array of surface detector stations (tanks) to detect the secondary particle showers generated by ultra-high energy cosmic rays. Due to the rare nature of ultra-high energy cosmic rays, it is important to have a high reliability on tank communications, ensuring no valuable data is lost. The Auger North site employs a peer-to-peer paradigm, the Wireless Architecture for Hard Real-Time Embedded Networks (WAHREN), designed specifically for highly reliable message delivery over fixed networks, under hard real-time deadlines. The WAHREN design included two retransmission protocols, Micro- and Macro- retransmission. To fully understand how each retransmission protocol increased the reliability of communications, this analysis evaluated the system without using either retransmission protocol (Case-0), both Micro- and Macro-retransmission individually (Micro and Macro), and Micro- and Macro-retransmission combined. This thesis used a multimodal modeling methodology to prove that a performance and reliability analysis of WAHREN was possible, and provided the results of the analysis. A multimodal approach was necessary because these processes were driven by different mathematical models. The results from this analysis can be used as a framework for making design decisions for the Auger North communication system.

Development of a 1-D Catalyzed Diesel Particulate Filter Model for Simulation of the Performance and the Oxidation of Particulate Matter and Nitrogen Oxides Using Passive Oxidation and Active Regeneration Engine Experimental Data

Back-pressure on a diesel engine equipped with an aftertreatment system is a function of the pressure drop across the individual components of the aftertreatment system, typically, a diesel oxidation catalyst (DOC), catalyzed particulate filter (CPF) and selective catalytic reduction (SCR) catalyst. Pressure drop across the CPF is a function of the mass flow rate and the temperature of the exhaust flowing through it as well as the mass of particulate matter (PM) retained in the substrate wall and the cake layer that forms on the substrate wall. Therefore, in order to control the back-pressure on the engine at low levels and to minimize the fuel consumption, it is important to control the PM mass retained in the CPF. Chemical reactions involving the oxidation of PM under passive oxidation and active regeneration conditions can be utilized with computer numerical models in the engine control unit (ECU) to control the pressure drop across the CPF. Hence, understanding and predicting the filtration and oxidation of PM in the CPF and the effect of these processes on the pressure drop across the CPF are necessary for developing control strategies for the aftertreatment system to reduce back-pressure on the engine and in turn fuel consumption particularly from active regeneration. Numerical modeling of CPF's has been proven to reduce development time and the cost of aftertreatment systems used in production as well as to facilitate understanding of the internal processes occurring during different operating conditions that the particulate filter is subjected to. A numerical model of the CPF was developed in this research work which was calibrated to data from passive oxidation and active regeneration experiments in order to determine the kinetic parameters for oxidation of PM and nitrogen oxides along with the model filtration parameters. The research results include the comparison between the model and the experimental data for pressure drop, PM mass retained, filtration efficiencies, CPF outlet gas temperatures and species (NO2) concentrations out of the CPF. Comparisons of PM oxidation reaction rates obtained from the model calibration to the data from the experiments for ULSD, 10 and 20% biodiesel-blended fuels are presented.

NEW MICROFLUIDIC SYSTEM TO INCREASE ROBUSTNESS OF ELECTRODE PERFORMANCE AND DEVELOP POINT-OF-CARE HEMATOCRIT DEVICE

The present dissertation aimed to develop a new microfluidic system for a point-of-care hematocrit device. Stabilization of microfluidic systems via surfactant additives and integration of semipermeable SnakeSkin® membranes was investigated. Both methods stabilized the microfluidic systems by controlling electrolysis bubbles. Surfactant additives, Triton X-100 and SDS stabilized promoted faster bubble detachment at electrode surfaces by lowering surface tension and decreased gas bubble formation by increasing gas solubility. The SnakeSkin® membranes blocked bubbles from entering the microchannel and thus less disturbance to the electric field by bubbles occurred in the microchannel. Platinum electrode performance was improved by carbonizing electrode surface using red blood cells. Irreversibly adsorbed RBCs lysed on platinum electrode surfaces and formed porous carbon layers while current response measurements. The formed carbon layers increase the platinum electrode surface area and thus electrode performance was improved by 140 %. The microfluidic system was simplified by employing DC field to use as a platform for a point-of-care hematocrit device. Feasibility of the microfluidic system for hematocrit determination was shown via current response measurements of red blood cell suspensions in phosphate buffered saline and plasma media. The linear trendline of current responses over red blood cell concentration was obtained in both phosphate buffered saline and plasma media. This research suggested that a new and simple microfluidic system could be a promising solution to develop an inexpensive and reliable point-of-care hematocrit device.