Resilience in Cloud Computing for Critical Systems. Resilience, Dependability, Reliability in the use of Cloud Computing in Critical Systems in Public Organizations.

La informática se está convirtiendo en la quinta utilidad (gas, agua, luz, teléfono) en parte debido al impacto de Cloud Computing en las mayorías de las organizaciones. Este uso de informática es usada por cada vez más tipos de sistemas, incluidos Sistemas Críticos. Esto tiene un impacto en la complejidad internad y la fiabilidad de los sistemas de la organización y los que se ofrecen a los clientes. Este trabajo investiga el uso de Cloud Computing por sistemas críticos, centrándose en las dependencias y especialmente en la fiabilidad de estos sistemas. Se han presentado algunos ejemplos de su uso, y aunque su utilización en sistemas críticos no está extendido, se presenta cual puede llegar a ser su impacto. El objetivo de este trabajo es primero definir un modelo que pueda representar de una forma cuantitativa las interdependencias en fiabilidad y interdependencia para las organizaciones que utilicen estos sistemas, y aplicar este modelo en un sistema crítico del campo de sanidad y mostrar sus resultados. Los conceptos de “macro-dependability” y “micro-dependability” son introducidos en el modelo para la definición de interdependencia y para analizar la fiabilidad de sistemas que dependen de otros sistemas. ABSTRACT With the increasing utilization of Internet services and cloud computing by most organizations (both private and public), it is clear that computing is becoming the 5th utility (along with water, electricity, telephony and gas). These technologies are used for almost all types of systems, and the number is increasing, including Critical Infrastructure systems. Even if Critical Infrastructure systems appear not to rely directly on cloud services, there may be hidden inter-dependencies. This is true even for private cloud computing, which seems more secure and reliable. The critical systems can began in some cases with a clear and simple design, but evolved as described by Egan to "rafted" networks. Because they are usually controlled by one or few organizations, even when they are complex systems, their dependencies can be understood. The organization oversees and manages changes. These CI systems have been affected by the introduction of new ICT models like global communications, PCs and the Internet. Even virtualization took more time to be adopted by Critical systems, due to their strategic nature, but once that these technologies have been proven in other areas, at the end they are adopted as well, for different reasons such as costs. A new technology model is happening now based on some previous technologies (virtualization, distributing and utility computing, web and software services) that are offered in new ways and is called cloud computing. The organizations are migrating more services to the cloud; this will have impact in their internal complexity and in the reliability of the systems they are offering to the organization itself and their clients. Not always this added complexity and associated risks to their reliability are seen. As well, when two or more CI systems are interacting, the risks of one can affect the rest, sharing the risks. This work investigates the use of cloud computing by critical systems, and is focused in the dependencies and reliability of these systems. Some examples are presented together with the associated risks. A framework is introduced for analysing the dependability and resilience of a system that relies on cloud services and how to improve them. As part of the framework, the concepts of micro and macro dependability are introduced to explain the internal and external dependability on services supplied by an external cloud. A pharmacovigilance model system has been used for framework validation.

Brain injury MRI simulator based on theoretical models of neuroanatomic damage

In order to improve the body of knowledge about brain injury impairment is essential to develop image database with different types of injuries. This paper proposes a new methodology to model three types of brain injury: stroke, tumor and traumatic brain injury; and implements a system to navigate among simulated MRI studies. These studies can be used on research studies, to validate new processing methods and as an educational tool, to show different types of brain injury and how they affect to neuroanatomic structures.

Enhancing regression models for complex systems using evolutionary techniques for feature engineering

This work proposes an automatic methodology for modeling complex systems. Our methodology is based on the combination of Grammatical Evolution and classical regression to obtain an optimal set of features that take part of a linear and convex model. This technique provides both Feature Engineering and Symbolic Regression in order to infer accurate models with no effort or designer's expertise requirements. As advanced Cloud services are becoming mainstream, the contribution of data centers in the overall power consumption of modern cities is growing dramatically. These facilities consume from 10 to 100 times more power per square foot than typical office buildings. Modeling the power consumption for these infrastructures is crucial to anticipate the effects of aggressive optimization policies, but accurate and fast power modeling is a complex challenge for high-end servers not yet satisfied by analytical approaches. For this case study, our methodology minimizes error in power prediction. This work has been tested using real Cloud applications resulting on an average error in power estimation of 3.98%. Our work improves the possibilities of deriving Cloud energy efficient policies in Cloud data centers being applicable to other computing environments with similar characteristics.

Server power modeling for run-time energy optimization of cloud computing facilities

As advanced Cloud services are becoming mainstream, the contribution of data centers in the overall power consumption of modern cities is growing dramatically. The average consumption of a single data center is equivalent to the energy consumption of 25.000 households. Modeling the power consumption for these infrastructures is crucial to anticipate the effects of aggressive optimization policies, but accurate and fast power modeling is a complex challenge for high-end servers not yet satisfied by analytical approaches. This work proposes an automatic method, based on Multi-Objective Particle Swarm Optimization, for the identification of power models of enterprise servers in Cloud data centers. Our approach, as opposed to previous procedures, does not only consider the workload consolidation for deriving the power model, but also incorporates other non traditional factors like the static power consumption and its dependence with temperature. Our experimental results shows that we reach slightly better models than classical approaches, but simul- taneously simplifying the power model structure and thus the numbers of sensors needed, which is very promising for a short-term energy prediction. This work, validated with real Cloud applications, broadens the possibilities to derive efficient energy saving techniques for Cloud facilities.

Crowdsourcing without a crowd : Reliable online species identification using Bayesian models to minimize crowd size

Acknowledgment This research is supported by an award made by the RCUK Digital Economy program to the University of Aberdeen’s dot.rural Digital Economy Hub (ref. EP/G066051/1).

Reconfigurable computing for Monte Carlo simulations: results and prospects of the Janus project

We describe Janus, a massively parallel FPGA-based computer optimized for the simulation of spin glasses, theoretical models for the behavior of glassy materials. FPGAs (as compared to GPUs or many-core processors) provide a complementary approach to massively parallel computing. In particular, our model problem is formulated in terms of binary variables, and floating-point operations can be (almost) completely avoided. The FPGA architecture allows us to run many independent threads with almost no latencies in memory access, thus updating up to 1024 spins per cycle. We describe Janus in detail and we summarize the physics results obtained in four years of operation of this machine; we discuss two types of physics applications: long simulations on very large systems (which try to mimic and provide understanding about the experimental non equilibrium dynamics), and low-temperature equilibrium simulations using an artificial parallel tempering dynamics. The time scale of our non-equilibrium simulations spans eleven orders of magnitude (from picoseconds to a tenth of a second). On the other hand, our equilibrium simulations are unprecedented both because of the low temperatures reached and for the large systems that we have brought to equilibrium. A finite-time scaling ansatz emerges from the detailed comparison of the two sets of simulations. Janus has made it possible to perform spin glass simulations that would take several decades on more conventional architectures. The paper ends with an assessment of the potential of possible future versions of the Janus architecture, based on state-of-the-art technology.

A study of a soft computing based method for 3D scenario reconstruction

Several recent works deal with 3D data in mobile robotic problems, e.g., mapping. Data comes from any kind of sensor (time of flight, Kinect or 3D lasers) that provide a huge amount of unorganized 3D data. In this paper we detail an efficient approach to build complete 3D models using a soft computing method, the Growing Neural Gas (GNG). As neural models deal easily with noise, imprecision, uncertainty or partial data, GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. We present a comprehensive study on GNG parameters to ensure the best result at the lowest time cost. From this GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.

A compact difference scheme for numerical solutions of second order dual-phase-lagging models of microscale heat transfer

Dual-phase-lagging (DPL) models constitute a family of non-Fourier models of heat conduction that allow for the presence of time lags in the heat flux and the temperature gradient. These lags may need to be considered when modeling microscale heat transfer, and thus DPL models have found application in the last years in a wide range of theoretical and technical heat transfer problems. Consequently, analytical solutions and methods for computing numerical approximations have been proposed for particular DPL models in different settings. In this work, a compact difference scheme for second order DPL models is developed, providing higher order precision than a previously proposed method. The scheme is shown to be unconditionally stable and convergent, and its accuracy is illustrated with numerical examples.

Towards a real-time 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors

In this project, we propose the implementation of a 3D object recognition system which will be optimized to operate under demanding time constraints. The system must be robust so that objects can be recognized properly in poor light conditions and cluttered scenes with significant levels of occlusion. An important requirement must be met: the system must exhibit a reasonable performance running on a low power consumption mobile GPU computing platform (NVIDIA Jetson TK1) so that it can be integrated in mobile robotics systems, ambient intelligence or ambient assisted living applications. The acquisition system is based on the use of color and depth (RGB-D) data streams provided by low-cost 3D sensors like Microsoft Kinect or PrimeSense Carmine. The range of algorithms and applications to be implemented and integrated will be quite broad, ranging from the acquisition, outlier removal or filtering of the input data and the segmentation or characterization of regions of interest in the scene to the very object recognition and pose estimation. Furthermore, in order to validate the proposed system, we will create a 3D object dataset. It will be composed by a set of 3D models, reconstructed from common household objects, as well as a handful of test scenes in which those objects appear. The scenes will be characterized by different levels of occlusion, diverse distances from the elements to the sensor and variations on the pose of the target objects. The creation of this dataset implies the additional development of 3D data acquisition and 3D object reconstruction applications. The resulting system has many possible applications, ranging from mobile robot navigation and semantic scene labeling to human-computer interaction (HCI) systems based on visual information.

Computational models for improved diagnosis and prognosis of stroke using robot-based biomarkers

Stroke is a leading cause of death and permanent disability worldwide, affecting millions of individuals. Traditional clinical scores for assessment of stroke-related impairments are inherently subjective and limited by inter-rater and intra-rater reliability, as well as floor and ceiling effects. In contrast, robotic technologies provide objective, highly repeatable tools for quantification of neurological impairments following stroke. KINARM is an exoskeleton robotic device that provides objective, reliable tools for assessment of sensorimotor, proprioceptive and cognitive brain function by means of a battery of behavioral tasks. As such, KINARM is particularly useful for assessment of neurological impairments following stroke. This thesis introduces a computational framework for assessment of neurological impairments using the data provided by KINARM. This is done by achieving two main objectives. First, to investigate how robotic measurements can be used to estimate current and future abilities to perform daily activities for subjects with stroke. We are able to predict clinical scores related to activities of daily living at present and future time points using a set of robotic biomarkers. The findings of this analysis provide a proof of principle that robotic evaluation can be an effective tool for clinical decision support and target-based rehabilitation therapy. The second main objective of this thesis is to address the emerging problem of long assessment time, which can potentially lead to fatigue when assessing subjects with stroke. To address this issue, we examine two time reduction strategies. The first strategy focuses on task selection, whereby KINARM tasks are arranged in a hierarchical structure so that an earlier task in the assessment procedure can be used to decide whether or not subsequent tasks should be performed. The second strategy focuses on time reduction on the longest two individual KINARM tasks. Both reduction strategies are shown to provide significant time savings, ranging from 30% to 90% using task selection and 50% using individual task reductions, thereby establishing a framework for reduction of assessment time on a broader set of KINARM tasks. All in all, findings of this thesis establish an improved platform for diagnosis and prognosis of stroke using robot-based biomarkers.

Dynamic Models under Uncertainty for Large-Scale Enterprise Systems

Thesis (Ph.D.)--University of Washington, 2016-06

Design and implementation of a windows-based parallel computing environment for large scale optimization

A parallel computing environment to support optimization of large-scale engineering systems is designed and implemented on Windows-based personal computer networks, using the master-worker model and the Parallel Virtual Machine (PVM). It is involved in decomposition of a large engineering system into a number of smaller subsystems optimized in parallel on worker nodes and coordination of subsystem optimization results on the master node. The environment consists of six functional modules, i.e. the master control, the optimization model generator, the optimizer, the data manager, the monitor, and the post processor. Object-oriented design of these modules is presented. The environment supports steps from the generation of optimization models to the solution and the visualization on networks of computers. User-friendly graphical interfaces make it easy to define the problem, and monitor and steer the optimization process. It has been verified by an example of a large space truss optimization. (C) 2004 Elsevier Ltd. All rights reserved.

Frequency and temporal effects in linear optical quantum computing

Typically linear optical quantum computing (LOQC) models assume that all input photons are completely indistinguishable. In practice there will inevitably be nonidealities associated with the photons and the experimental setup which will introduce a degree of distinguishability between photons. We consider a nondeterministic optical controlled-NOT gate, a fundamental LOQC gate, and examine the effect of temporal and spectral distinguishability on its operation. We also consider the effect of utilizing nonideal photon counters, which have finite bandwidth and time response.

Advanced computing for systems biology

Systems biology is based on computational modelling and simulation of large networks of interacting components. Models may be intended to capture processes, mechanisms, components and interactions at different levels of fidelity. Input data are often large and geographically disperse, and may require the computation to be moved to the data, not vice versa. In addition, complex system-level problems require collaboration across institutions and disciplines. Grid computing can offer robust, scaleable solutions for distributed data, compute and expertise. We illustrate some of the range of computational and data requirements in systems biology with three case studies: one requiring large computation but small data (orthologue mapping in comparative genomics), a second involving complex terabyte data (the Visible Cell project) and a third that is both computationally and data-intensive (simulations at multiple temporal and spatial scales). Authentication, authorisation and audit systems are currently not well scalable and may present bottlenecks for distributed collaboration particularly where outcomes may be commercialised. Challenges remain in providing lightweight standards to facilitate the penetration of robust, scalable grid-type computing into diverse user communities to meet the evolving demands of systems biology.