Dynamic Workload Parallelization and System Calibration on Single-Chip Cloud Computer

Many-core systems are emerging from the need of more computational power and power efficiency. However there are many issues which still revolve around the many-core systems. These systems need specialized software before they can be fully utilized and the hardware itself may differ from the conventional computational systems. To gain efficiency from many-core system, programs need to be parallelized. In many-core systems the cores are small and less powerful than cores used in traditional computing, so running a conventional program is not an efficient option. Also in Network-on-Chip based processors the network might get congested and the cores might work at different speeds. In this thesis is, a dynamic load balancing method is proposed and tested on Intel 48-core Single-Chip Cloud Computer by parallelizing a fault simulator. The maximum speedup is difficult to obtain due to severe bottlenecks in the system. In order to exploit all the available parallelism of the Single-Chip Cloud Computer, a runtime approach capable of dynamically balancing the load during the fault simulation process is used. The proposed dynamic fault simulation approach on the Single-Chip Cloud Computer shows up to 45X speedup compared to a serial fault simulation approach. Many-core systems can draw enormous amounts of power, and if this power is not controlled properly, the system might get damaged. One way to manage power is to set power budget for the system. But if this power is drawn by just few cores of the many, these few cores get extremely hot and might get damaged. Due to increase in power density multiple thermal sensors are deployed on the chip area to provide realtime temperature feedback for thermal management techniques. Thermal sensor accuracy is extremely prone to intra-die process variation and aging phenomena. These factors lead to a situation where thermal sensor values drift from the nominal values. This necessitates efficient calibration techniques to be applied before the sensor values are used. In addition, in modern many-core systems cores have support for dynamic voltage and frequency scaling. Thermal sensors located on cores are sensitive to the core's current voltage level, meaning that dedicated calibration is needed for each voltage level. In this thesis a general-purpose software-based auto-calibration approach is also proposed for thermal sensors to calibrate thermal sensors on different range of voltages.

Mesh partitioning and load balancing for distributed memory parallel systems

A method is outlined for optimising graph partitions which arise in mapping unstructured mesh calculations to parallel computers. The method employs a relative gain iterative technique to both evenly balance the workload and minimise the number and volume of interprocessor communications. A parallel graph reduction technique is also briefly described and can be used to give a global perspective to the optimisation. The algorithms work efficiently in parallel as well as sequentially and when combined with a fast direct partitioning technique (such as the Greedy algorithm) to give an initial partition, the resulting two-stage process proves itself to be both a powerful and flexible solution to the static graph-partitioning problem. Experiments indicate that the resulting parallel code can provide high quality partitions, independent of the initial partition, within a few seconds. The algorithms can also be used for dynamic load-balancing, reusing existing partitions and in this case the procedures are much faster than static techniques, provide partitions of similar or higher quality and, in comparison, involve the migration of a fraction of the data.

Real-time analytics on large dynamic graphs

In today's fast-paced and interconnected digital world, the data generated by an increasing number of applications is being modeled as dynamic graphs. The graph structure encodes relationships among data items, while the structural changes to the graphs as well as the continuous stream of information produced by the entities in these graphs make them dynamic in nature. Examples include social networks where users post status updates, images, videos, etc.; phone call networks where nodes may send text messages or place phone calls; road traffic networks where the traffic behavior of the road segments changes constantly, and so on. There is a tremendous value in storing, managing, and analyzing such dynamic graphs and deriving meaningful insights in real-time. However, a majority of the work in graph analytics assumes a static setting, and there is a lack of systematic study of the various dynamic scenarios, the complexity they impose on the analysis tasks, and the challenges in building efficient systems that can support such tasks at a large scale. In this dissertation, I design a unified streaming graph data management framework, and develop prototype systems to support increasingly complex tasks on dynamic graphs. In the first part, I focus on the management and querying of distributed graph data. I develop a hybrid replication policy that monitors the read-write frequencies of the nodes to decide dynamically what data to replicate, and whether to do eager or lazy replication in order to minimize network communication and support low-latency querying. In the second part, I study parallel execution of continuous neighborhood-driven aggregates, where each node aggregates the information generated in its neighborhoods. I build my system around the notion of an aggregation overlay graph, a pre-compiled data structure that enables sharing of partial aggregates across different queries, and also allows partial pre-computation of the aggregates to minimize the query latencies and increase throughput. Finally, I extend the framework to support continuous detection and analysis of activity-based subgraphs, where subgraphs could be specified using both graph structure as well as activity conditions on the nodes. The query specification tasks in my system are expressed using a set of active structural primitives, which allows the query evaluator to use a set of novel optimization techniques, thereby achieving high throughput. Overall, in this dissertation, I define and investigate a set of novel tasks on dynamic graphs, design scalable optimization techniques, build prototype systems, and show the effectiveness of the proposed techniques through extensive evaluation using large-scale real and synthetic datasets.

Detecting Danger: Applying a Novel Immunological Concept to Intrusion Detection Systems'

INTRODUCTION In recent years computer systems have become increasingly complex and consequently the challenge of protecting these systems has become increasingly difficult. Various techniques have been implemented to counteract the misuse of computer systems in the form of firewalls, antivirus software and intrusion detection systems. The complexity of networks and dynamic nature of computer systems leaves current methods with significant room for improvement. Computer scientists have recently drawn inspiration from mechanisms found in biological systems and, in the context of computer security, have focused on the human immune system (HIS). The human immune system provides an example of a robust, distributed system that provides a high level of protection from constant attacks. By examining the precise mechanisms of the human immune system, it is hoped the paradigm will improve the performance of real intrusion detection systems. This paper presents an introduction to recent developments in the field of immunology. It discusses the incorporation of a novel immunological paradigm, Danger Theory, and how this concept is inspiring artificial immune systems (AIS). Applications within the context of computer security are outlined drawing direct reference to the underlying principles of Danger Theory and finally, the current state of intrusion detection systems is discussed and improvements suggested.

Large-scale dynamic hydrofracturing, healing and fracture network characterization

Permeability of a rock is a dynamic property that varies spatially and temporally. Fractures provide the most efficient channels for fluid flow and thus directly contribute to the permeability of the system. Fractures usually form as a result of a combination of tectonic stresses, gravity (i.e. lithostatic pressure) and fluid pressures. High pressure gradients alone can cause fracturing, the process which is termed as hydrofracturing that can determine caprock (seal) stability or reservoir integrity. Fluids also transport mass and heat, and are responsible for the formation of veins by precipitating minerals within open fractures. Veining (healing) thus directly influences the rock’s permeability. Upon deformation these closed factures (veins) can refracture and the cycle starts again. This fracturing-healing-refacturing cycle is a fundamental part in studying the deformation dynamics and permeability evolution of rock systems. This is generally accompanied by fracture network characterization focusing on network topology that determines network connectivity. Fracture characterization allows to acquire quantitative and qualitative data on fractures and forms an important part of reservoir modeling. This thesis highlights the importance of fracture-healing and veins’ mechanical properties on the deformation dynamics. It shows that permeability varies spatially and temporally, and that healed systems (veined rocks) should not be treated as fractured systems (rocks without veins). Field observations also demonstrate the influence of contrasting mechanical properties, in addition to the complexities of vein microstructures that can form in low-porosity and permeability layered sequences. The thesis also presents graph theory as a characterization method to obtain statistical measures on evolving network connectivity. It also proposes what measures a good reservoir should have to exhibit potentially large permeability and robustness against healing. The results presented in the thesis can have applications for hydrocarbon and geothermal reservoir exploration, mining industry, underground waste disposal, CO2 injection or groundwater modeling.

Dynamic set pieces for CAMBADA team

Robotics is an emergent branch of engineering that involves the conception, manufacture, and control of robots. It is a multidisciplinary field that combines electronics, design, computer science, artificial intelligence, mechanics and nanotechnology. Its evolution results in machines that are able to perform tasks with some level of complexity. Multi-agent systems is a researching topic within robotics, thus they allow the solving of higher complexity problems, through the execution of simple routines. Robotic soccer allows the study and development of robotics and multiagent systems, as the agents have to work together as a team, having in consideration most problems found in our quotidian, as for example adaptation to a highly dynamic environment as it is the one of a soccer game. CAMBADA is the robotic soccer team belonging to the group of research IRIS from IEETA, composed by teachers, researchers and students of the University of Aveiro, which annually has as main objective the participation in the RoboCup, in the Middle Size League. The purpose of this work is to improve the coordination in set pieces situations. This thesis introduces a new behavior and the adaptation of the already existing ones in the offensive situation, as well as the proposal of a new positioning method in defensive situations. The developed work was incorporated within the competition software of the robots. Which allows the presentation, in this dissertation, of the experimental results obtained, through simulation software as well as through the physical robots on the laboratory.

Dynamic instabilities in scalar neural field equations with space-dependent delays

In this paper we consider a class of scalar integral equations with a form of space-dependent delay. These non-local models arise naturally when modelling neural tissue with active axons and passive dendrites. Such systems are known to support a dynamic (oscillatory) Turing instability of the homogeneous steady state. In this paper we develop a weakly nonlinear analysis of the travelling and standing waves that form beyond the point of instability. The appropriate amplitude equations are found to be the coupled mean-field Ginzburg-Landau equations describing a Turing-Hopf bifurcation with modulation group velocity of O(1). Importantly we are able to obtain the coefficients of terms in the amplitude equations in terms of integral transforms of the spatio-temporal kernels defining the neural field equation of interest. Indeed our results cover not only models with axonal or dendritic delays but those which are described by a more general distribution of delayed spatio-temporal interactions. We illustrate the predictive power of this form of analysis with comparison against direct numerical simulations, paying particular attention to the competition between standing and travelling waves and the onset of Benjamin-Feir instabilities.

Dynamic Coculture of a Prevascularized Engineered Bone Construct

The generation of functional, vascularized tissues is a key challenge for the field of tissue engineering. Before clinical implantations of tissue engineered bone constructs can succeed, in vitro fabrication needs to address limitations in large-scale tissue development, including controlled osteogenesis and an inadequate vasculature network to prevent necrosis of large constructs. The tubular perfusion system (TPS) bioreactor is an effective culturing method to augment osteogenic differentiation and maintain viability of human mesenchymal stem cell (hMSC)-seeded scaffolds while they are developed in vitro. To further enhance this process, we developed a novel osteogenic growth factors delivery system for dynamically cultured hMSCs using microparticles encapsulated in three-dimensional alginate scaffolds. In light of this increased differentiation, we characterized the endogenous cytokine distribution throughout the TPS bioreactor. An advantageous effect in the ‘outlet’ portion of the uniaxial growth chamber was discovered due to the system’s downstream circulation and the unique modular aspect of the scaffolds. This unique trait allowed us to carefully tune the differentiation behavior of specific cell populations. We applied the knowledge gained from the growth profile of the TPS bioreactor to culture a high-volume bone composite in a 3D-printed femur mold. This resulted in a tissue engineered bone construct with a volume of 200cm3, a 20-fold increase over previously reported sizes. We demonstrated high viability of the cultured cells throughout the culture period as well as early signs of osteogenic differentiation. Taking one step closer toward a viable implant and minimize tissue necrosis after implantation, we designed a composite construct by coculturing endothelial cells (ECs) and differentiating hMSCs, encouraging prevascularization and anastomosis of the graft with the host vasculature. We discovered the necessity of cell to cell proximity between the two cell types as well as preference for the natural cell binding capabilities of hydrogels like collagen. Notably, the results suggested increased osteogenic and angiogenic potential of the encapsulated cells when dynamically cultured in the TPS bioreactor, suggesting a synergistic effect between coculture and applied shear stress. This work highlights the feasibility of fabricating a high-volume, prevascularized tissue engineered bone construct for the regeneration of a critical size defect.

Detecting Danger: Applying a Novel Immunological Concept to Intrusion Detection Systems'

INTRODUCTION In recent years computer systems have become increasingly complex and consequently the challenge of protecting these systems has become increasingly difficult. Various techniques have been implemented to counteract the misuse of computer systems in the form of firewalls, antivirus software and intrusion detection systems. The complexity of networks and dynamic nature of computer systems leaves current methods with significant room for improvement. Computer scientists have recently drawn inspiration from mechanisms found in biological systems and, in the context of computer security, have focused on the human immune system (HIS). The human immune system provides an example of a robust, distributed system that provides a high level of protection from constant attacks. By examining the precise mechanisms of the human immune system, it is hoped the paradigm will improve the performance of real intrusion detection systems. This paper presents an introduction to recent developments in the field of immunology. It discusses the incorporation of a novel immunological paradigm, Danger Theory, and how this concept is inspiring artificial immune systems (AIS). Applications within the context of computer security are outlined drawing direct reference to the underlying principles of Danger Theory and finally, the current state of intrusion detection systems is discussed and improvements suggested.

Improving the use of G-CSF during chemotherapy using physiological mathematical modelling : a quantitative systems pharmacology approach

La diminution des doses administrées ou même la cessation complète d'un traitement chimiothérapeutique est souvent la conséquence de la réduction du nombre de neutrophiles, qui sont les globules blancs les plus fréquents dans le sang. Cette réduction dans le nombre absolu des neutrophiles, aussi connue sous le nom de myélosuppression, est précipitée par les effets létaux non spécifiques des médicaments anti-cancéreux, qui, parallèlement à leur effet thérapeutique, produisent aussi des effets toxiques sur les cellules saines. Dans le but d'atténuer cet impact myélosuppresseur, on administre aux patients un facteur de stimulation des colonies de granulocytes recombinant humain (rhG-CSF), une forme exogène du G-CSF, l'hormone responsable de la stimulation de la production des neutrophiles et de leurs libération dans la circulation sanguine. Bien que les bienfaits d'un traitement prophylactique avec le G-CSF pendant la chimiothérapie soient bien établis, les protocoles d'administration demeurent mal définis et sont fréquemment déterminés ad libitum par les cliniciens. Avec l'optique d'améliorer le dosage thérapeutique et rationaliser l'utilisation du rhG-CSF pendant le traitement chimiothérapeutique, nous avons développé un modèle physiologique du processus de granulopoïèse, qui incorpore les connaissances actuelles de pointe relatives à la production des neutrophiles des cellules souches hématopoïétiques dans la moelle osseuse. À ce modèle physiologique, nous avons intégré des modèles pharmacocinétiques/pharmacodynamiques (PK/PD) de deux médicaments: le PM00104 (Zalypsis®), un médicament anti-cancéreux, et le rhG-CSF (filgrastim). En se servant des principes fondamentaux sous-jacents à la physiologie, nous avons estimé les paramètres de manière exhaustive sans devoir recourir à l'ajustement des données, ce qui nous a permis de prédire des données cliniques provenant de 172 patients soumis au protocol CHOP14 (6 cycles de chimiothérapie avec une période de 14 jours où l'administration du rhG-CSF se fait du jour 4 au jour 13 post-chimiothérapie). En utilisant ce modèle physio-PK/PD, nous avons démontré que le nombre d'administrations du rhG-CSF pourrait être réduit de dix (pratique actuelle) à quatre ou même trois administrations, à condition de retarder le début du traitement prophylactique par le rhG-CSF. Dans un souci d'applicabilité clinique de notre approche de modélisation, nous avons investigué l'impact de la variabilité PK présente dans une population de patients, sur les prédictions du modèle, en intégrant des modèles PK de population (Pop-PK) des deux médicaments. En considérant des cohortes de 500 patients in silico pour chacun des cinq scénarios de variabilité plausibles et en utilisant trois marqueurs cliniques, soient le temps au nadir des neutrophiles, la valeur du nadir, ainsi que l'aire sous la courbe concentration-effet, nous avons établi qu'il n'y avait aucune différence significative dans les prédictions du modèle entre le patient-type et la population. Ceci démontre la robustesse de l'approche que nous avons développée et qui s'apparente à une approche de pharmacologie quantitative des systèmes (QSP). Motivés par l'utilisation du rhG-CSF dans le traitement d'autres maladies, comme des pathologies périodiques telles que la neutropénie cyclique, nous avons ensuite soumis l'étude du modèle au contexte des maladies dynamiques. En mettant en évidence la non validité du paradigme de la rétroaction des cytokines pour l'administration exogène des mimétiques du G-CSF, nous avons développé un modèle physiologique PK/PD novateur comprenant les concentrations libres et liées du G-CSF. Ce nouveau modèle PK a aussi nécessité des changements dans le modèle PD puisqu’il nous a permis de retracer les concentrations du G-CSF lié aux neutrophiles. Nous avons démontré que l'hypothèse sous-jacente de l'équilibre entre la concentration libre et liée, selon la loi d'action de masse, n'est plus valide pour le G-CSF aux concentrations endogènes et mènerait en fait à la surestimation de la clairance rénale du médicament. En procédant ainsi, nous avons réussi à reproduire des données cliniques obtenues dans diverses conditions (l'administration exogène du G-CSF, l'administration du PM00104, CHOP14). Nous avons aussi fourni une explication logique des mécanismes responsables de la réponse physiologique aux deux médicaments. Finalement, afin de mettre en exergue l’approche intégrative en pharmacologie adoptée dans cette thèse, nous avons démontré sa valeur inestimable pour la mise en lumière et la reconstruction des systèmes vivants complexes, en faisant le parallèle avec d’autres disciplines scientifiques telles que la paléontologie et la forensique, où une approche semblable a largement fait ses preuves. Nous avons aussi discuté du potentiel de la pharmacologie quantitative des systèmes appliquées au développement du médicament et à la médecine translationnelle, en se servant du modèle physio-PK/PD que nous avons mis au point.

Secure, dynamic and distributed access control stack for database applications

In database applications, access control security layers are mostly developed from tools provided by vendors of database management systems and deployed in the same servers containing the data to be protected. This solution conveys several drawbacks. Among them we emphasize: 1) if policies are complex, their enforcement can lead to performance decay of database servers; 2) when modifications in the established policies implies modifications in the business logic (usually deployed at the client-side), there is no other possibility than modify the business logic in advance and, finally, 3) malicious users can issue CRUD expressions systematically against the DBMS expecting to identify any security gap. In order to overcome these drawbacks, in this paper we propose an access control stack characterized by: most of the mechanisms are deployed at the client-side; whenever security policies evolve, the security mechanisms are automatically updated at runtime and, finally, client-side applications do not handle CRUD expressions directly. We also present an implementation of the proposed stack to prove its feasibility. This paper presents a new approach to enforce access control in database applications, this way expecting to contribute positively to the state of the art in the field.

Secure, dynamic and distributed access control stack for database applications

In database applications, access control security layers are mostly developed from tools provided by vendors of database management systems and deployed in the same servers containing the data to be protected. This solution conveys several drawbacks. Among them we emphasize: (1) if policies are complex, their enforcement can lead to performance decay of database servers; (2) when modifications in the established policies implies modifications in the business logic (usually deployed at the client-side), there is no other possibility than modify the business logic in advance and, finally, 3) malicious users can issue CRUD expressions systematically against the DBMS expecting to identify any security gap. In order to overcome these drawbacks, in this paper we propose an access control stack characterized by: most of the mechanisms are deployed at the client-side; whenever security policies evolve, the security mechanisms are automatically updated at runtime and, finally, client-side applications do not handle CRUD expressions directly. We also present an implementation of the proposed stack to prove its feasibility. This paper presents a new approach to enforce access control in database applications, this way expecting to contribute positively to the state of the art in the field.

Modelling of an efficient dynamic smart solar photovoltaic power grid system

A smart solar photovoltaic grid system is an advent of innovation coherence of information and communications technology (ICT) with power systems control engineering via the internet [1]. This thesis designs and demonstrates a smart solar photovoltaic grid system that is selfhealing, environmental and consumer friendly, but also with the ability to accommodate other renewable sources of energy generation seamlessly, creating a healthy competitive energy industry and optimising energy assets efficiency. This thesis also presents the modelling of an efficient dynamic smart solar photovoltaic power grid system by exploring the maximum power point tracking efficiency, optimisation of the smart solar photovoltaic array through modelling and simulation to improve the quality of design for the solar photovoltaic module. In contrast, over the past decade quite promising results have been published in literature, most of which have not addressed the basis of the research questions in this thesis. The Levenberg-Marquardt and sparse based algorithms have proven to be very effective tools in helping to improve the quality of design for solar photovoltaic modules, minimising the possible relative errors in this thesis. Guided by theoretical and analytical reviews in literature, this research has carefully chosen the MatLab/Simulink software toolbox for modelling and simulation experiments performed on the static smart solar grid system. The auto-correlation coefficient results obtained from the modelling experiments give an accuracy of 99% with negligible mean square error (MSE), root mean square error (RMSE) and standard deviation. This thesis further explores the design and implementation of a robust real-time online solar photovoltaic monitoring system, establishing a comparative study of two solar photovoltaic tracking systems which provide remote access to the harvested energy data. This research made a landmark innovation in designing and implementing a unique approach for online remote access solar photovoltaic monitoring systems providing updated information of the energy produced by the solar photovoltaic module at the site location. In addressing the challenge of online solar photovoltaic monitoring systems, Darfon online data logger device has been systematically integrated into the design for a comparative study of the two solar photovoltaic tracking systems examined in this thesis. The site location for the comparative study of the solar photovoltaic tracking systems is at the National Kaohsiung University of Applied Sciences, Taiwan, R.O.C. The overall comparative energy output efficiency of the azimuthal-altitude dual-axis over the 450 stationary solar photovoltaic monitoring system as observed at the research location site is about 72% based on the total energy produced, estimated money saved and the amount of CO2 reduction achieved. Similarly, in comparing the total amount of energy produced by the two solar photovoltaic tracking systems, the overall daily generated energy for the month of July shows the effectiveness of the azimuthal-altitude tracking systems over the 450 stationary solar photovoltaic system. It was found that the azimuthal-altitude dual-axis tracking systems were about 68.43% efficient compared to the 450 stationary solar photovoltaic systems. Lastly, the overall comparative hourly energy efficiency of the azimuthal-altitude dual-axis over the 450 stationary solar photovoltaic energy system was found to be 74.2% efficient. Results from this research are quite promising and significant in satisfying the purpose of the research objectives and questions posed in the thesis. The new algorithms introduced in this research and the statistical measures applied to the modelling and simulation of a smart static solar photovoltaic grid system performance outperformed other previous works in reviewed literature. Based on this new implementation design of the online data logging systems for solar photovoltaic monitoring, it is possible for the first time to have online on-site information of the energy produced remotely, fault identification and rectification, maintenance and recovery time deployed as fast as possible. The results presented in this research as Internet of things (IoT) on smart solar grid systems are likely to offer real-life experiences especially both to the existing body of knowledge and the future solar photovoltaic energy industry irrespective of the study site location for the comparative solar photovoltaic tracking systems. While the thesis has contributed to the smart solar photovoltaic grid system, it has also highlighted areas of further research and the need to investigate more on improving the choice and quality design for solar photovoltaic modules. Finally, it has also made recommendations for further research in the minimization of the absolute or relative errors in the quality and design of the smart static solar photovoltaic module.

A Replacement Technique to Maximize Task Reuse in Reconfigurable Systems

Dynamically reconfigurable hardware is a promising technology that combines in the same device both the high performance and the flexibility that many recent applications demand. However, one of its main drawbacks is the reconfiguration overhead, which involves important delays in the task execution, usually in the order of hundreds of milliseconds, as well as high energy consumption. One of the most powerful ways to tackle this problem is configuration reuse, since reusing a task does not involve any reconfiguration overhead. In this paper we propose a configuration replacement policy for reconfigurable systems that maximizes task reuse in highly dynamic environments. We have integrated this policy in an external taskgraph execution manager that applies task prefetch by loading and executing the tasks as soon as possible (ASAP). However, we have also modified this ASAP technique in order to make the replacements more flexible, by taking into account the mobility of the tasks and delaying some of the reconfigurations. In addition, this replacement policy is a hybrid design-time/run-time approach, which performs the bulk of the computations at design time in order to save run-time computations. Our results illustrate that the proposed strategy outperforms other state-ofthe-art replacement policies in terms of reuse rates and achieves near-optimal reconfiguration overhead reductions. In addition, by performing the bulk of the computations at design time, we reduce the execution time of the replacement technique by 10 times with respect to an equivalent purely run-time one.

Infomobility for “Car-Driver” Systems: Reference Model and Case Study

Part 21: Mobility and Logistics