BUILDING EFFICIENT AND COST-EFFECTIVE CLOUD-BASED BIG DATA MANAGEMENT SYSTEMS

In today’s big data world, data is being produced in massive volumes, at great velocity and from a variety of different sources such as mobile devices, sensors, a plethora of small devices hooked to the internet (Internet of Things), social networks, communication networks and many others. Interactive querying and large-scale analytics are being increasingly used to derive value out of this big data. A large portion of this data is being stored and processed in the Cloud due the several advantages provided by the Cloud such as scalability, elasticity, availability, low cost of ownership and the overall economies of scale. There is thus, a growing need for large-scale cloud-based data management systems that can support real-time ingest, storage and processing of large volumes of heterogeneous data. However, in the pay-as-you-go Cloud environment, the cost of analytics can grow linearly with the time and resources required. Reducing the cost of data analytics in the Cloud thus remains a primary challenge. In my dissertation research, I have focused on building efficient and cost-effective cloud-based data management systems for different application domains that are predominant in cloud computing environments. In the first part of my dissertation, I address the problem of reducing the cost of transactional workloads on relational databases to support database-as-a-service in the Cloud. The primary challenges in supporting such workloads include choosing how to partition the data across a large number of machines, minimizing the number of distributed transactions, providing high data availability, and tolerating failures gracefully. I have designed, built and evaluated SWORD, an end-to-end scalable online transaction processing system, that utilizes workload-aware data placement and replication to minimize the number of distributed transactions that incorporates a suite of novel techniques to significantly reduce the overheads incurred both during the initial placement of data, and during query execution at runtime. In the second part of my dissertation, I focus on sampling-based progressive analytics as a means to reduce the cost of data analytics in the relational domain. Sampling has been traditionally used by data scientists to get progressive answers to complex analytical tasks over large volumes of data. Typically, this involves manually extracting samples of increasing data size (progressive samples) for exploratory querying. This provides the data scientists with user control, repeatable semantics, and result provenance. However, such solutions result in tedious workflows that preclude the reuse of work across samples. On the other hand, existing approximate query processing systems report early results, but do not offer the above benefits for complex ad-hoc queries. I propose a new progressive data-parallel computation framework, NOW!, that provides support for progressive analytics over big data. In particular, NOW! enables progressive relational (SQL) query support in the Cloud using unique progress semantics that allow efficient and deterministic query processing over samples providing meaningful early results and provenance to data scientists. NOW! enables the provision of early results using significantly fewer resources thereby enabling a substantial reduction in the cost incurred during such analytics. Finally, I propose NSCALE, a system for efficient and cost-effective complex analytics on large-scale graph-structured data in the Cloud. The system is based on the key observation that a wide range of complex analysis tasks over graph data require processing and reasoning about a large number of multi-hop neighborhoods or subgraphs in the graph; examples include ego network analysis, motif counting in biological networks, finding social circles in social networks, personalized recommendations, link prediction, etc. These tasks are not well served by existing vertex-centric graph processing frameworks whose computation and execution models limit the user program to directly access the state of a single vertex, resulting in high execution overheads. Further, the lack of support for extracting the relevant portions of the graph that are of interest to an analysis task and loading it onto distributed memory leads to poor scalability. NSCALE allows users to write programs at the level of neighborhoods or subgraphs rather than at the level of vertices, and to declaratively specify the subgraphs of interest. It enables the efficient distributed execution of these neighborhood-centric complex analysis tasks over largescale graphs, while minimizing resource consumption and communication cost, thereby substantially reducing the overall cost of graph data analytics in the Cloud. The results of our extensive experimental evaluation of these prototypes with several real-world data sets and applications validate the effectiveness of our techniques which provide orders-of-magnitude reductions in the overheads of distributed data querying and analysis in the Cloud.

Seasonal changes of heat and moisture fluxes from the Caspian Sea surface and its effect on synoptic systems with heavy rainfalls in southern shores of the sea during 2005-2010

Caspian Sea with its unique characteristics is a significant source to supply required heat and moisture for passing weather systems over the north of Iran. Investigation of heat and moisture fluxes in the region and their effects on these systems that could lead to floods and major financial and human losses is essential in weather forecasting. Nowadays by improvement of numerical weather and climate prediction models and the increasing need to more accurate forecasting of heavy rainfall, the evaluation and verification of these models has been become much more important. In this study we have used the WRF model as a research-practical one with many valuable characteristics and flexibilities. In this research, the effects of heat and moisture fluxes of Caspian Sea on the synoptic and dynamical structure of 20 selective systems associated with heavy rainfall in the southern shores of Caspian Sea are investigated. These systems are selected based on the rainfall data gathered by three local stations named: Rasht, Babolsar and Gorgan in different seasons during a five-year period (2005-2010) with maximum amount of rainfall through the 24 hours of a day. In addition to synoptic analyses of these systems, the WRF model with and without surface flues was run using the two nested grids with the horizontal resolutions of 12 and 36 km. The results show that there are good consistencies between the predicted distribution of rainfall field, time of beginning and end of rainfall by the model and the observations. But the model underestimates the amounts of rainfall and the maximum difference with the observation is about 69%. Also, no significant changes in the results are seen when the domain and the resolution of computations are changed. The other noticeable point is that the systems are severely weakened by removing heat and moisture fluxes and thereby the amounts of large scale rainfall are decreased up to 77% and the convective rainfalls tend to zero.

Evaluation of the conductor-like screening model for real solvents for the prediction of the water activity coefficient at infinite dilution in ionic liquids

Ionic liquids (ILs) have attracted great attention, from both industry and academia, as alternative fluids for very different types of applications. The large number of cations and anions allow a wide range of physical and chemical characteristics to be designed. However, the exhaustive measurement of all these systems is impractical, thus requiring the use of a predictive model for their study. In this work, the predictive capability of the conductor-like screening model for real solvents (COSMO-RS), a model based on unimolecular quantum chemistry calculations, was evaluated for the prediction water activity coefficient at infinite dilution, gamma(infinity)(w), in several classes of ILs. A critical evaluation of the experimental and predicted data using COSMO-RS was carried out. The global average relative deviation was found to be 27.2%, indicating that the model presents a satisfactory prediction ability to estimate gamma(infinity)(w) in a broad range of ILs. The results also showed that the basicity of the ILs anions plays an important role in their interaction with water, and it considerably determines the enthalpic behavior of the binary mixtures composed by Its and water. Concerning the cation effect, it is possible to state that generally gamma(infinity)(w) increases with the cation size, but it is shown that the cation-anion interaction strength is also important and is strongly correlated to the anion ability to interact with water. The results here reported are relevant in the understanding of ILs-water interactions and the impact of the various structural features of its on the gamma(infinity)(w) as these allow the development of guidelines for the choice of the most suitable lLs with enhanced interaction with water.

In-situ Molibdenum X-ray powder diffraction study of the early hydration of cementitious systems on a humidity chamber

The durability of cement-based construction materials depends on the environmental conditions during their service life. A further factor is the microstructure of the cement bulk, established by formation of cement hydrates. The development of the phases and microstructure under given conditions is responsible of the high strength of cementitious materials. The investigation on the early hydration behavior of cements and cementing systems has been for a long time a very important area of research: understanding the chemical reactions that lead to hardening is fundamental for the prediction of performances and durability of the materials. The production of 1 ton of Ordinary Portland Cement, OPC, releases into the atmosphere ~0.97 tons of CO2. This implies that the overall CO2 emissions from the cement industry are 6% of all anthropogenic carbon dioxide. An alternative to reduce the CO2 footprint consists on the development of eco-cements composed by less calcite demanding phases, such as belite and ye'elimite. That is the case of Belite-Ye’elimite cements (BY). Since the reactivity of belite is not quick enough, these materials develop low mechanical strengths at intermediate hydration ages. A possible solution to this problem goes through the production of cements which jointly contain alite with the two previously mentioned phases, named as Belite-Alite-Ye’elimite (BAY) cements. The reaction of alite and ye'elimite with water will develop cements with high mechanical strengths at early ages, while belite will contribute to later values. The final goal is to understand the hydration mechanisms of a variety of cementing systems (OPC, BAY and pure phases) as a function of water content, superplasticizer additives and type and content of sulfate source. In order to do so, in-situ laboratory humidity chambers with Molybdenum X-ray Powder diffraction are employed. In the first 2h of hydration, reaction degree (α) of ye'elimite had been decreased for superplasticizer.

Implementation of an intelligent sensor for measurement and prediction of solar radiation and atmospheric temperature

Dissertação de mestrado, Engenharia Electrónica e Telecomunicações, Faculdade de Ciências e Tecnologia, Universidade do Algarve, 2011

Adaptive Software Fault Prediction Approach Using Object-Oriented Metrics

As users continually request additional functionality, software systems will continue to grow in their complexity, as well as in their susceptibility to failures. Particularly for sensitive systems requiring higher levels of reliability, faulty system modules may increase development and maintenance cost. Hence, identifying them early would support the development of reliable systems through improved scheduling and quality control. Research effort to predict software modules likely to contain faults, as a consequence, has been substantial. Although a wide range of fault prediction models have been proposed, we remain far from having reliable tools that can be widely applied to real industrial systems. For projects with known fault histories, numerous research studies show that statistical models can provide reasonable estimates at predicting faulty modules using software metrics. However, as context-specific metrics differ from project to project, the task of predicting across projects is difficult to achieve. Prediction models obtained from one project experience are ineffective in their ability to predict fault-prone modules when applied to other projects. Hence, taking full benefit of the existing work in software development community has been substantially limited. As a step towards solving this problem, in this dissertation we propose a fault prediction approach that exploits existing prediction models, adapting them to improve their ability to predict faulty system modules across different software projects.

Average-case analysis of power consumption in embedded systems

Power efficiency is one of the most important constraints in the design of embedded systems since such systems are generally driven by batteries with limited energy budget or restricted power supply. In every embedded system, there are one or more processor cores to run the software and interact with the other hardware components of the system. The power consumption of the processor core(s) has an important impact on the total power dissipated in the system. Hence, the processor power optimization is crucial in satisfying the power consumption constraints, and developing low-power embedded systems. A key aspect of research in processor power optimization and management is “power estimation”. Having a fast and accurate method for processor power estimation at design time helps the designer to explore a large space of design possibilities, to make the optimal choices for developing a power efficient processor. Likewise, understanding the processor power dissipation behaviour of a specific software/application is the key for choosing appropriate algorithms in order to write power efficient software. Simulation-based methods for measuring the processor power achieve very high accuracy, but are available only late in the design process, and are often quite slow. Therefore, the need has arisen for faster, higher-level power prediction methods that allow the system designer to explore many alternatives for developing powerefficient hardware and software. The aim of this thesis is to present fast and high-level power models for the prediction of processor power consumption. Power predictability in this work is achieved in two ways: first, using a design method to develop power predictable circuits; second, analysing the power of the functions in the code which repeat during execution, then building the power model based on average number of repetitions. In the first case, a design method called Asynchronous Charge Sharing Logic (ACSL) is used to implement the Arithmetic Logic Unit (ALU) for the 8051 microcontroller. The ACSL circuits are power predictable due to the independency of their power consumption to the input data. Based on this property, a fast prediction method is presented to estimate the power of ALU by analysing the software program, and extracting the number of ALU-related instructions. This method achieves less than 1% error in power estimation and more than 100 times speedup in comparison to conventional simulation-based methods. In the second case, an average-case processor energy model is developed for the Insertion sort algorithm based on the number of comparisons that take place in the execution of the algorithm. The average number of comparisons is calculated using a high level methodology called MOdular Quantitative Analysis (MOQA). The parameters of the energy model are measured for the LEON3 processor core, but the model is general and can be used for any processor. The model has been validated through the power measurement experiments, and offers high accuracy and orders of magnitude speedup over the simulation-based method.

A pro-active and dynamic prediction assistance using BaranC framework

Monitoring user interaction activities provides the basis for creating a user model that can be used to predict user behaviour and enable user assistant services. The BaranC framework provides components that perform UI monitoring (and collect all associated context data), builds a user model, and supports services that make use of the user model. In this case study, a Next-App prediction service is built to demonstrate the use of the framework and to evaluate the usefulness of such a prediction service. Next-App analyses a user's data, learns patterns, makes a model for a user, and finally predicts based on the user model and current context, what application(s) the user is likely to want to use. The prediction is pro-active and dynamic; it is dynamic both in responding to the current context, and also in that it responds to changes in the user model, as might occur over time as a user's habits change. Initial evaluation of Next-App indicates a high-level of satisfaction with the service.

A next application prediction service using the BaranC framework

Predicting user behaviour enables user assistant services provide personalized services to the users. This requires a comprehensive user model that can be created by monitoring user interactions and activities. BaranC is a framework that performs user interface (UI) monitoring (and collects all associated context data), builds a user model, and supports services that make use of the user model. A prediction service, Next-App, is built to demonstrate the use of the framework and to evaluate the usefulness of such a prediction service. Next-App analyses a user's data, learns patterns, makes a model for a user, and finally predicts, based on the user model and current context, what application(s) the user is likely to want to use. The prediction is pro-active and dynamic, reflecting the current context, and is also dynamic in that it responds to changes in the user model, as might occur over time as a user's habits change. Initial evaluation of Next-App indicates a high-level of satisfaction with the service.

Experimental and modeling studies of forced convection storage and drying systems for sweet potatoes

Sweet potato is an important strategic agricultural crop grown in many countries around the world. The roots and aerial vine components of the crop are used for both human consumption and, to some extent as a cheap source of animal feed. In spite of its economic value and growing contribution to health and nutrition, harvested sweet potato roots and aerial vine components has limited shelf-life and is easily susceptible to post-harvest losses. Although post-harvest losses of both sweet potato roots and aerial vine components is significant, there is no information available that will support the design and development of appropriate storage and preservation systems. In this context, the present study was initiated to improve scientific knowledge about sweet potato post-harvest handling. Additionally, the study also seeks to develop a PV ventilated mud storehouse for storage of sweet potato roots under tropical conditions. In study one, airflow resistance of sweet potato aerial vine components was investigated. The influence of different operating parameters such as airflow rate, moisture content and bulk depth at different levels on airflow resistance was analyzed. All the operating parameters were observed to have significant (P < 0.01) effect on airflow resistance. Prediction models were developed and were found to adequately describe the experimental pressure drop data. In study two, the resistance of airflow through unwashed and clean sweet potato roots was investigated. The effect of sweet potato roots shape factor, surface roughness, orientation to airflow, and presence of soil fraction on airflow resistance was also assessed. The pressure drop through unwashed and clean sweet potato roots was observed to increase with higher airflow, bed depth, root grade composition, and presence of soil fraction. The physical properties of the roots were incorporated into a modified Ergun model and compared with a modified Shedd’s model. The modified Ergun model provided the best fit to the experimental data when compared with the modified Shedd’s model. In study three, the effect of sweet potato root size (medium and large), different air velocity and temperature on the cooling/or heating rate and time of individual sweet potato roots were investigated. Also, a simulation model which is based on the fundamental solution of the transient equations was proposed for estimating the cooling and heating time at the centre of sweet potato roots. The results showed that increasing air velocity during cooling and heating significantly (P < 0.05) affects the cooling and heating times. Furthermore, the cooling and heating times were significantly different (P < 0.05) among medium and large size sweet potato roots. Comparison of the simulation results with experimental data confirmed that the transient simulation model can be used to accurately estimate the cooling and heating times of whole sweet potato roots under forced convection conditions. In study four, the performance of charcoal evaporative cooling pad configurations for integration into sweet potato roots storage systems was investigated. The experiments were carried out at different levels of air velocity, water flow rates, and three pad configurations: single layer pad (SLP), double layers pad (DLP) and triple layers pad (TLP) made out of small and large size charcoal particles. The results showed that higher air velocity has tremendous effect on pressure drop. Increasing the water flow rate above the range tested had no practical benefits in terms of cooling. It was observed that DLP and TLD configurations with larger wet surface area for both types of pads provided high cooling efficiencies. In study five, CFD technique in the ANSYS Fluent software was used to simulate airflow distribution in a low-cost mud storehouse. By theoretically investigating different geometries of air inlet, plenum chamber, and outlet as well as its placement using ANSYS Fluent software, an acceptable geometry with uniform air distribution was selected and constructed. Experimental measurements validated the selected design. In study six, the performance of the developed PV ventilated system was investigated. Field measurements showed satisfactory results of the directly coupled PV ventilated system. Furthermore, the option of integrating a low-cost evaporative cooling system into the mud storage structure was also investigated. The results showed a reduction of ambient temperature inside the mud storehouse while relative humidity was enhanced. The ability of the developed storage system to provide and maintain airflow, temperature and relative humidity which are the key parameters for shelf-life extension of sweet potato roots highlight its ability to reduce post-harvest losses at the farmer level, particularly under tropical climate conditions.

Prediction of Length of Hospital Stay in Preterm Infants - A Case-Based Reasoning View

The length of stay of preterm infants in a neonatology service has become an issue of a growing concern, namely considering, on the one hand, the mothers and infants health conditions and, on the other hand, the scarce healthcare facilities own resources. Thus, a pro-active strategy for problem solving has to be put in place, either to improve the quality-of-service provided or to reduce the inherent financial costs. Therefore, this work will focus on the development of a diagnosis decision support system in terms of a formal agenda built on a Logic Programming approach to knowledge representation and reasoning, complemented with a case-based problem solving methodology to computing, that caters for the handling of incomplete, unknown, or even contradictory in-formation. The proposed model has been quite accurate in predicting the length of stay (overall accuracy of 84.9%) and by reducing the computational time with values around 21.3%.

A Case Based approach to assess Waiting Time Prediction at an Intensive Care Unity

Waiting time at an intensive care unity stands for a key feature in the assessment of healthcare quality. Nevertheless, its estimation is a difficult task, not only due to the different factors with intricate relations among them, but also with respect to the available data, which may be incomplete, self-contradictory or even unknown. However, its prediction not only improves the patients’ satisfaction but also enhance the quality of the healthcare being provided. To fulfill this goal, this work aims at the development of a decision support system that allows one to predict how long a patient should remain at an emergency unit, having into consideration all the remarks that were just stated above. It is built on top of a Logic Programming approach to knowledge representation and reasoning, complemented with a Case Base approach to computing.

Age Prediction through Pelvis X-Ray Images - A Case Based approach to Problem Solving

It is well known that the dimensions of the pelvic bones depend on the gender and vary with the age of the individual. Indeed, and as a matter of fact, this work will focus on the development of an intelligent decision support system to predict individual’s age based on pelvis’ dimensions criteria. On the one hand, some basic image processing technics were applied in order to extract the relevant features from pelvic X-rays. On the other hand, the computational framework presented here was built on top of a Logic Programming approach to knowledge representation and reasoning, that caters for the handling of incomplete, unknown, or even self-contradictory information, complemented with a Case Base approach to computing.

Dynamic Modeling and Seasonal Performance Evaluation of Air-to-Water Heat Pump Systems

In this Thesis a series of numerical models for the evaluation of the seasonal performance of reversible air-to-water heat pump systems coupled to residential and non-residential buildings are presented. The exploitation of the energy saving potential linked to the adoption of heat pumps is a hard task for designers due to the influence on their energy performance of several factors, like the external climate variability, the heat pump modulation capacity, the system control strategy and the hydronic loop configuration. The aim of this work is to study in detail all these aspects. In the first part of this Thesis a series of models which use a temperature class approach for the prediction of the seasonal performance of reversible air source heat pumps are shown. An innovative methodology for the calculation of the seasonal performance of an air-to-water heat pump has been proposed as an extension of the procedure reported by the European standard EN 14825. This methodology can be applied not only to air-to-water single-stage heat pumps (On-off HPs) but also to multi-stage (MSHPs) and inverter-driven units (IDHPs). In the second part, dynamic simulation has been used with the aim to optimize the control systems of the heat pump and of the HVAC plant. A series of dynamic models, developed by means of TRNSYS, are presented to study the behavior of On-off HPs, MSHPs and IDHPs. The main goal of these dynamic simulations is to show the influence of the heat pump control strategies and of the lay-out of the hydronic loop used to couple the heat pump to the emitters on the seasonal performance of the system. A particular focus is given to the modeling of the energy losses linked to on-off cycling.

Analysis of the impact of stationary energy storage systems in trolleybus grids using Simulink-based modelling

The voltage profile of the catenary between traction substations (TSSs) is affected by the trolleybus current intake and by its position with respect to the TSSs: the higher the current requested by the bus and the further the bus from the TSSs, the deeper the voltage drop. When the voltage drops below 500V, the trolleybus is forced to decrease its consumption by reducing its input current. This thesis deals with the analysis of the improvements that the installation of an BESS produces in the operation of a particularly loaded FS of the DC trolleybus network of the city of Bologna. The stationary BESS is charged by the TSSs during off-peak times and delivers the stored energy when the catenary is overloaded alleviating the load on the TSSs and reducing the voltage drops. Only IMC buses are considered in the prospect of a future disposal of all internal combustion engine vehicles. These trolleybuses cause deeper voltage drops because they absorb enough current to power their traction motor and recharge the on board battery. The control of the BESS aims to keep the catenary voltage within the admissible voltage range and makes sure that all physical limitations are met. A model of FS Marconi Trento Trieste is implemented in Simulink environment to simulate its daily operation and compare the behavior of the trolleybus network with and without BESS. From the simulation without BESS, the best location of the energy storage system is deduced, and the battery control is tuned. Furthermore, from the knowledge of the load curve and the battery control trans-characteristic, it is formulated a prediction of the voltage distribution at BESS connection point. The prediction is then compared with the simulation results to validate the Simulink model. The BESS allows to decrease the voltage drops along the catenary, the Joule losses and the current delivered by the TSSs, indicating that the BESS can be a solution to improve the operation of the trolleybus network.