Fault Tolerant Computing

The High Performance Computing (HPC) refers to the solution of complex problems by a group of servers, called cluster. The cluster as a whole is used for solving a single problem or a group of related problems. Initially, the solutions provided by HPC were limited to scientific research, but due to cost reductions and new business requirements, HPC can already be applied to data centers, software simulations, processing transactions and any resolution of business complex problems. The University of Boyacá developed the research project entitled "interaction of the components of the Microsoft HPC cluster (High Performance Computing) Server 2008 with MPI applications", which belongs to the distributed systems investigation line from the distributed systems and teleinformatics -GISDYTEL research group. This project will determine how the components that are part of information processing cluster Microsoft HPC (High Performance Computing) Server 2008 relate to each other to solve a highly complex problem with MPI applications. This article describes: The HP server cluster including all concerning concepts (Clusters, High Performance Computing and MPI), all the project infrastructure requirements, the creation process from the virtualization cluster nodes, passing through the domain creation and the implementation of MPI programs and the results analysis.

We propose Recursive Entropy (RE) as a universal organizing principle regulating stability across physics, AI, and number theory. Unlike classical entropy, which passively measures disorder, RE actively stabilizes system evolution through recursive feedback. We introduce Prime-Modulated Recursive Entropy (PMRE), where prime numbers act as intrinsic entropy stabilizers, preventing chaotic divergence in quantum systems, AI cognition, and black hole entropy dynamics. We present the Unified Recursive Entropy Master Equation (UREME).

integrating:
• Quantum Entropy Modulation: Recursive entropy governs wavefunction
collapse and entanglement evolution.
• AI Learning Stability: Prime-indexed entropy corrections regulate deep
learning feedback loops.
• Black Hole Information Preservation: Recursive entropy prevents paradoxical
information loss.
Additionally, we introduce Recursive Entropic Quantum Error Correction
(RE-QEC), stabilizing quantum coherence through entropy-driven fault tolerance. Numerical simulations validate RE stabilization across quantum mechanics, AI training, and prime gap distributions. This work establishes Recursive Entropy as a fundamental stabilizing force, revealing a deep entropic structure underlying physical laws and number theory.

This article introduces an on-line fault diagnosis (FD) system to detect and recognize open-phase faults in switched reluctance motors (SRMs). Both tasks, detection and recognition, are based on functions built with the same information but from different sources. Specifically, these functions are constructed from bus current measurement provided by a sensor and from the estimate of such a current provided by an extended Kalman filter (EKF) that performs the estimation from only rotor angular position measurements. In short, the FD system only requires two measurements for employment: bus current and angular position. In order to show its efficacy, results from numerical simulations (performed in a virtual test bench) are presented. Specifically, these simulations involve the dynamics of the SRM, including the magnetic phenomena caused by the analyzed faults. The motor dynamics were obtained with finite element simulations, which guarantee results close to the actual ones.

The paper describes a new interconnection network for massively parallel systems, referred to as star-connected cycles (SCC). The SCC graph presents an I/O-bounded structure that results in several advantages over variabledegree graphs like the star and the hypercube. The description of the SCC graph includes issues such as labelling of nodes, degree, diameter and symmetry. The paper also presents an optimal routeing algorithm for the SCC and efficient broadcasting algorithms with O(n) running time, with n being the dimensionality of the graph. A comparison with the cube-connected cycles (CCC) and other interconnection networks is included, indicating that, for even n, an n-SCC and a CCC of similar sizes have about the same diameter. In addition, it is shown that one-port broadcasting in an n-SCC graph can be accomplished with a running time better than or equal to that required by an n-star containing (n -1) times fewer nodes.

We study the benefits of microservices and containerization for web development by looking at their ability to speed up deployments and keep apps stable. Microservices lets you build separate web application pieces that developers can work on independently while treating each like a small system. Containerization delivers stable and reliable deployment settings that help teams fix fewer problems during and after release. The paper analyzes past issues of monolithic software, which made deployments slow and made the systems unsustainable due to high load. The study applies case study evaluation and qualitative analysis to measure the actual results of these technologies in business, particularly their ability to reduce system failures and provide faster scalability. Our research focuses on tracking how quickly systems launch and remain active. Our research shows that microservices and containerization help make web development more efficient and effective. Our findings include practical steps for businesses to follow when adopting these architectures, plus future research topics in software engineering.

An approach to consider computers and connected computer systems using structural, time, and information redundancies is proposed. An application of redundancy for reconfigurability and recoverability of computers and connected computer systems is discussed, gaining performance, reliability, and power-saving in operation. A paradigm of recoverability is introduced and, if followed, shifts connected computer systems toward real-time applications. Use of redundancy for connected computers is analysed in terms of recoverability, where two supportive algorithms of forward and backward tracing are proposed and explained. As an example, growth of mission reliability is formulated.

Fault tolerance is a critical aspect of ensuring the efficiency and reliability of High-Performance Computing (HPC) clusters, which are indispensable for handling largescale computational workloads in fields such as meteorology, molecular dynamics, and climate modeling. Traditional approaches like checkpointing and dynamic load balancing have demonstrated significant potential in mitigating the impact of faults. Innovations such as incremental checkpointing and predictive fault management have further optimized recovery times and resource utilization, enhancing overall system performance. However, these strategies pose trade-offs, including computational overhead and task migration complexities. By leveraging advancements in machine learning and mathematical modeling, modern fault tolerance mechanisms predict and preempt failures, reducing downtime and boosting system resilience. This paper explores optimized algorithms and strategies for fault tolerance in HPC clusters, emphasizing their application, efficiency, and potential for future enhancement.

We analytically investigate distributed circuit modeling of the tunable-enhanced Goos-Hänchen shift of light beams from a Graphene containing structure which supports TM surface waves. Here the coupling of the incident wave to the surface modes of the structure is used to enhance the Goos-Hänchen shift of the totally reflected wave. It is also shown that this large lateral shift can be controlled trough controlling the dispersion properties of the surface modes by applying an electrical voltage to the Graphene layer. A distributed circuit model is proposed for the Graphene containing structure and used to calculate the reflection coefficient of the structure. Phase of the reflection coefficient is then used to calculate the Goos-Hänchen shift. Our calculations show that by coupling the incident wave to the surface modes of the structure large Goos-Hänchen shift as high as 100 times of the free space wavelength can be achieved. Furthermore this large shift can be tuned by apply relat...

for VLSI, including selfchecking circuits and concurent checking techniques for temporary faults based on time redundancy. It cautions that emerging technological constraints and application requirements will expend dramatically the use of these techniques. In particular, various industrial sectors (e.g. railway control, satellites, avionics, telecommunications, control of critical automotive functions, medical electronics, industrial control, etc), have increasing needs for concurrent checking features. Some of these applications concern mass production and should support the standardization of such techniques and the development of commercial CAD tools supporting them. Furthermore, drastic device shrinking and increasing operating speeds that accompany the technological evolution to deeper submicron, reduces significantly the noise margins and increases dramatically the impact of transient faults. In addition various spurious faults are becoming predominant and require very complex test conditions. Under such conditions, test pattern generation complexity and test length make impossible the detection of such faults. As a consequence, technological progress will be blocked quickly if no particular actions are undertaken to cope with increasingly high soft-error rates and undetected spurious faults resulting on timing errors. The paper will discuss these emerging requirements and problems and describe how concurrent checking can be used to cope with.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Distributed computing systems have become a pivotal aspect of modern technology, enabling complex computations and tasks across various industries, including telecommunications, scientific research, and financial services. These systems provide scalability, fault tolerance, and resource sharing across multiple nodes, allowing for efficient handling of vast datasets. This paper discusses the characteristics, architectural styles, and middleware solutions that support distributed computing, with a focus on fault tolerance mechanisms and distributed consensus algorithms such as Paxos and Raft. Additionally, it compares notable frameworks like Apache Spark and Ray, which serve distinct roles in managing data processing and realtime computational tasks, respectively. The discussion highlights the importance of fault tolerance and resilience in ensuring the continuous operation of distributed systems in diverse applications.

Dealing with industrial applications, the implementation of condition monitoring schemes must overcome a critical limitation, that is, the lack of a priori information about fault patterns of the system under analysis. Indeed, classical diagnosis schemes, in general, outdo the membership probability of a measure in regard to predefined operating scenarios. However, dealing with noncharacterized systems, the knowledge about faulty operating scenarios is limited and, consequently, the diagnosis performance is insufficient. In this context, the novelty detection framework plays an essential role for monitoring systems in which the information about different operating scenarios is initially unavailable or restricted. The novelty detection approach begins with the assumption that only data corresponding to the healthy operation of the system under analysis is available. Thus, the challenge is to detect and learn additional scenarios during the operation of the system in order to complement the information obtained by the diagnosis scheme. This work has two main objectives: first, the presentation of novelty detection as the current trend toward the new paradigm of industrial condition monitoring and, second, the introduction to its applicability by means of analyses of different novelty detection strategies over a real industrial system based on rotatory machinery.

Providing fault tolerance especially to mission critical applications in order to detect transient and permanent faults and to recover from them is one of the main necessity for processor designers. However, fault tolerance for multi-threaded applications presents high performance degradations due to comparing the results of the instruction streams, checkpointing the entire system and recovering from the detected errors to an agreed state. In this study, we present FaulTM-multi, a fault tolerance scheme for multi threaded applications running on transactional memory hardware which reduces these performance degradations. FaulTM-multi decreases the performance degradation of lockstepping, a conventional fault detection scheme, from 23% and 9% to 10% and 2% for lock-based parallel and TM applications respectively. Also, FaulTM-multi creates 28% less checkpoints compared to Rebound, the state of the art checkpointing scheme.

Fault-tolerance has become an essential concern for processor designers due to increasing transient and permanent fault rates. Executing instruction streams redundantly in chip multi processors (CMP) provides high reliability since it can detect both transient and permanent faults and silent data corruptions. However, comparing the results of the instruction streams, checkpointing the entire system and recovering from the detected errors present high performance degradation in execution time. This paper presents FaulTMmulti, transactional memory based fault detection and recovery scheme for multi threaded applications running on transactional memory hardware in order to reduce these performance degradations.

Fault-tolerance has become an essential concern for processor designers due to increasing soft-error rates. In this study, we are motivated by the fact that Transactional Memory (TM) hardware provides an ideal base upon which to build a fault-tolerant system. We show how it is possible to provide low-cost faulttolerance for serial programs by using a minimallymodified Hardware Transactional Memory (HTM) that features lazy conflict detection, lazy data versioning. This scheme, called FaulTM, employs a hybrid hardware-software fault-tolerance technique. On the software side, FaulTM programming model is able to provide the flexibility for programmers to decide between performance and reliability. Our experimental results indicate that FaulTM produces relatively less performance overhead by reducing the number of comparisons and by leveraging already proposed TM hardware. We also conduct experiments which indicate that the baseline FaulTM design has a good error coverage. To the best of our knowledge, this is the first architectural fault-tolerance proposal using Hardware Transactional Memory.

Mobile ad hoc networks are envisaged to play a vital role in ubiquitous networking owing to their mobility support without relying on infrastructure-based design. Conversely, the same feature makes routing in these networks challenging as compared to the typical wired networks. As a result typical routing protocols designed for wired networks are not appropriate for these networks. A number of routing protocols have emerged over the last few years which can be generally classified as proactive and reactive routing protocols. In this research, we analyze and compare three most important routing protocols from both categories in terms of throughput, end to end delay and packet delivery fraction. This comparison is useful in understanding the requirements and challenges for routing protocols in mobile and ad hoc setting and forms the basis of designing a new routing protocol which we plan to present in future. Our simulation results based on simulations carried out using Network Simula...

In this paper, a fault detection and isolation (FDI) approach using a bank of interval observers is developed. From the methodological point of view, a bank of interval observers is designed according to different dynamical models of the system under different modes (healthy or faulty). Each interval observer matches one system mode while all the interval observers monitor the system simultaneously. In order to guarantee FDI, a set of FDI conditions based on invariant set notions are established. These conditions ensure that the considered faults can be accurately isolated after a period of monitoring time. Finally, simulation results are used to present the effectiveness of the approach.

Sml. NAME OF FUNDING/SPONSORING 'lD. OFFICE SYMBOL 9. PROCUREMENT INSTRUMENT IDENTIFICATION NUMBER 4ORGANIZATION (fi ppIicbiuj AFOSR NM AFOSR-84-0132* Sc. ADDRESS (City. State wnd ZIP Code) 10. SOURCE OF FUNDING NOS. PROGRAM PROJECT TASK WORK UNIT ELEMENT NO. NO. NO. NO.

Active fault detection for a stable open-loop linear time invariant system is considered. The optimal active fault detection setup is developed around an estimator based architecture. The auxiliary signal and estimator are then designed in order to maximize detection performance. Equations are derived which relate the estimator design to the nominal residual signal covariance. The relationship between the auxiliary input and the system performance degradation constraint is considered. The effect of estimator gain and excitation signal frequency on the dual Youla-Jabr-Bongiorno-Kucera parameter is investigated. An LTI input shaping filter is added to allow for added MIMO system complexity. Theory developed for the general output zeroing problem is combined with the extended MIMO architecture in order to arrive at a solution without the nominal performance penalty usually associated with active fault detection. Furthermore, the effect of the control input is considered and formulated as an additional optimisation criterion, resulting in an average-case optimisation scenario.

Optimised Active Fault Detection for an Open Loop Stable System R. Busch Department of Electrical and Electronic Engineering, University of Stellenbosch, Private Bag X1, Matieland 7602, South Africa. Dissertation: PhD November 2016 Active fault detection for a stable open-loop linear time invariant system is considered. The optimal active fault detection setup is developed around an estimator based architecture. The auxiliary signal and estimator are then designed in order to maximize detection performance. Equations are derived which relate the estimator design to the nominal residual signal covariance. The relationship between the auxiliary input and the system performance degradation constraint is considered. The effect of estimator gain and excitation signal frequency on the dual Youla-Jabr-BongiornoKucera parameter is investigated. An LTI input shaping filter is added to allow for added MIMO system complexity. Theory developed for the general output zeroing problem is combined ...

There is a significant growth in the use of solar photovoltaics (PV) for clean and sustainable renewable energy. The ease of installation and expansion of PV power plants makes them suitable for grid-connected operation. However, increasing the size of the PV power plant will make it difficult to detect and classify faults, which leads to lower system efficiency and reliability. Therefore, this article proposes a method for detecting and classifying faults in PV systems in order to fix them more quickly and efficiently. For this purpose, the data of current and voltage are collected from every panel for a period of time in normal case and for three common fault types (open circuit, short circuit, and shading), and afterwards converted into wavelet transform images. Then a deep learning approach is used to detect, classify, and locate defective panels in a PV system. The obtained results show that the deep learning approach based on Resnet50, and voltage images was 100% accurate compared to the deep learning approach based on current images. In this methodology there is no need for additional sensors since they are embedded with panels and sent to main computer. Since the voltage parameter has the best accuracy scenario, it is converted to images, then ResNet-50 is applied. So, every panel can be detected and classified, and as each panel is numbered, the fault location can be readily determined.

Anti-Lock Braking Systems (ABS) and Brake-by-Wire Systems (BBW) are safety-critical applications by nature. Such systems are required to demonstrate high degrees of dependability. Fault-tolerance is the primary means to achieve dependability at runtime and has been an active research area for decades. Fault-tolerance is usually achieved in traditional embedded computing systems through redundancy and voting methods. In such systems, hardware units, actuators, sensors, and communication networks are replicated where special voters vote against faulty units. In addition to traditional hardware and software redundancy, hybrid and reconfiguration-based approaches to fault-tolerance are evolving. In this article, we present a reconfiguration-based fault-tolerant approach to achieve high dependability in ABS BBW braking systems. The proposed architecture makes use of other components of less safety-critical systems to maintain high dependability in the more safety-critical systems. This i...

Graceful degradation is an approach for developing dependable safety-critical embedded applications, where redundant active or standby resources are used to cope with faults through system reconfiguration at run-time. Compared to traditional hardware and software redundancy, it is a promising technique that may achieve dependability with a significant reduction in cost, size, weight, and power requirements. Checkpointing protocols, which are necessary components of degrading systems, support task migration through state preservation. They allow real-time embedded systems to recover from any failure by restarting from the last well-defined and consistent state, thus preserving the progress of computations that have been achieved. This paper demonstrates and applies the graceful degradation concept to achieve fault tolerance in an unmanned aerial vehicle (UAV) real-time embedded system. A checkpointing protocol is used to reserve the state of the avionics of the UAV system. Faults were injected during run-time causing one of the system's stability critical control tasks to fail. The system was able successfully to recover by restarting the affected critical task(s) on a different processor with last valid consistent state(s). This paper presents the architecture, fault injection scheme, and the results of the tests performed, which demonstrate the viability of graceful degradation in our tested UAV. I.

This paper is based on a five-day workshop on “Atomicity in System Design and Execution ” that took place in Schloss Dagstuhl in Germany [5] in April 2004 and was attended by 32 people from different scientific communities. 1 The participants included researchers

The article describes the function of the BCH code decoder for correcting of double errors in main memory. Some basic algebraic concepts needed to understand the structure of the BCH code, which is used to secure the main memory of a "Multiprocessor Computing System", are explained and the method of decoding this code is shown as an example.

In this study, a modified phenomenological model has been proposed by merging the Suzen-Huang model and the Yoon-Han thrust model for two types of single plasma actuators and plasma synthetic jet actuators, in different geometries and different working and environmental conditions. The model introduced in the present work is based on the thrust induced by plasma. With this generalization and modification, this model overcomes the drawbacks of the standard Suzen-Huang model, i.e., lack of correct estimation of the nonlinear relationship between the applied voltage and the amount of thrust induced by the plasma and not considering the influence of parameters such as the thickness of dielectric and dielectric constant, the thickness of the exposed electrode, and the alternating current frequency). Applying this model on a single plasma actuator shows the accuracy and correctness of this model. Also, by generalizing the present model for the annular plasma synthetic jet actuators, the dependence of the maximum charge density and body force on the diameter of the actuator was included in the model. Validation of the present model for the annular plasma synthetic jet actuator shows that the model is able to adapt itself well to changing the diameter of the actuator, working conditions, geometry and materials of the actuator and make a good estimate of the results.

There is a current and growing crisis in power management for the entire range of power‐performance computer infrastructure design points—from mobile to enterprise to cloud computing. Recent strategic visioning studies, including a white paper by the Computing Community Consortium on 21st Century Computer Architecture1 and the NITRD Program 2012 Strategic Plan2, emphasize the importance of energy‐efficient computing for sustaining advancements in information technology and addressing critical societal challenges. The exploration of holistic power optimization and management solutions that cut across multiple layers of the computing stack and infrastructure will better enable available opportunities for maximizing energy efficiency.

Two-dimensional RAID arrays maintain separate row and column parities for all their disks. Depending on their organization, they can tolerate between two and three concurrent disk failures without losing any data. We propose to enhance the robustness of these arrays by replacing a small fraction of these drives with storage class memory devices, and demonstrate how such a pairing is

In this paper we consider the problem of reconfiguring processor arrays subject to computational loads that alternate between two modes. A strict mode is characterized by a heavy computational load and severe constraints on response time while a relaxed mode is characterized by a relatively light computational load and relaxed constraints on response time. In the strict mode, reconfiguration is performed by a distributed local algorithm in order to achieve fast recovery from faults. In the relaxed mode, a global reconfiguration algorithm is used to restore the system to a state that maximizes the probability that future faults occurring in subsequent strict modes will be repairable. Several new results are given for this problem. Efficient reconfiguration algorithms are described for a number of general classes of architectures. These general algorithms obviate the need for architecture-specific algorithms for architectures in these classes. We show that it is unlikely that similar algorithms can be obtained for related classes of architectures since the reconflguration problem for these classes is NP-complete. Finally, a general approximation algorithm is described that can be used for any architecture. Experimental results are given, suggesting that our algorithms are very effective.

We harden the Hadoop Distributed File System (HDFS) against fail-silent (non fail-stop) behaviors that result from memory corruption and software bugs using a new approach: selective and lightweight versioning (SLEEVE). With this approach, actions performed by important subsystems of HDFS (e.g., namespace management) are checked by a second implementation of the subsystem that uses lightweight, approximate data structures. We show that HARDFS detects and recovers from a wide range of fail-silent behaviors caused by random bit flips, targeted corruptions, and real software bugs. In particular, HARDFS handles 90% of the fail-silent faults that result from random memory corruption and correctly detects and recovers from 100% of 78 targeted corruptions and 5 real-world bugs. Moreover, it recovers orders of magnitude faster than full reboot by using micro-recovery. The extra protection in HARDFS incurs minimal performance and space overheads.

This Research Paper is totally concentrated to define different memory systems that are present in the market, and what is their importance in today’s generation. In this paper, we review the different hierarchies of the memory systems. It talks about cache-memory based systems and its various levels. Cache memories along with the virtual memories and processor registers form a field of memory hierarchies that depends on the principle of locality of reference. Most applications show the temporal and spatial zones among order and data. Then it describes about RAM (Random Access Memory) and its types which include DRAM (Dynamic Random-Access Memory) and SRAM (Static Random-Access Memory), it also describes the flash memory and its importance because of its small size and large memory containing abilities Memory hierarchies are intended to keep most likely referenced items in the fastest devices.

A wireless sensor network is a collection of batterypowered sensor nodes distributed in a geographical area. Inmany applications, such networks are left unattended for along period of time. These networks suffer from the problemslike high energy consumption, high latency time, and end- to-end low packet delivery ratio. To design a protocol that findsa trade-off between these problems is a challenging task. Inorder to mitigate energy consumption issue, different existingMedia Access Control (MAC) protocols such as S-MAC, RMAC,HEMAC, and Congestion-less Single Token MAC protocols havebeen proposed which ensure better packet delivery but fail toensure energy efficiency due to high end-to-end latency. Theproblem of high end-to-end latency is resolved with the existingrouting protocols such as Fault Tolerant Multilevel Routingprotocol (FMS)and Enhanced Tree Routing (ETR) protocol.AS2-MAC and Multi Token based MAC protocol are able toimprove the end-to-end packet delivery ratio. However, ...

With popularization of video streaming service in recent years, new video distribution technologies have been created. Currently, one of the most promising ones is the Moving Picture Expert Group Dynamic Adaptive Streaming over HTTP or MPEG-DASH. However, with the limitation of the TCP/IP network structure, the end user quality of experience (QoE) may be affected. One issue that can affect user QoE is the workload of content servers. Thus, the imbalancing of server's workload comprising user's attendance can lead to a content server provider non optimized choice. This work presents a loadbalancing solution between MPEG-DASH video servers based on Software Defined Networks, using as a balancing workload metric the throughput of the content server. Resumo. Com a popularização do serviço de streaming de vídeo nosúltimos anos, novas tecnologias de distribuição de vídeo foram criadas. Uma das mais promissoras atualmenteé a chamada de Moving Picture Expert Group Dynamic Adaptive Streaming over HTTP, ou MPEG-DASH. Contudo, com a limitação da estrutura de rede TCP/IP, a Qualidade de Experiência (QoE) do usuário final pode ser afetada. Um dos fatores que podem afetar a QoE do usuárioé a carga de trabalho dos servidores de conteúdo. Assim, o desbalanceamento da carga de atendimento dos usuários entre os servidores pode gerar uma escolha não otimizada do provedor de conteúdo. Este trabalho apresenta uma solução de balanceamento de carga entre servidores de vídeo MPEG-DASH baseada em Redes Definidas por Software, utilizando como métrica de balanceamento a taxa de transferência do servidor de conteúdo.

Partial Bitstream Relocation (PBR) has been introduced in recent years, as a means to overcome the limitations of the traditional Xilinx Partial Reconfiguration flow, particularly in terms of the limited module placement, a fact that can greatly reduce the memory footprint of applications which require multiple implementations of the same module... However, PBR consumes scarce resources in hardware implementations, and introduces a prohibitive time overhead when done in software. This is particularly true in applications such as large scalable systems, which typically require multiple copies of the same module to accelerate a task, but in which the relocation time overhead might proof prohibitive. In order to find the best compromise between these approaches, we make use of the OORBIT tool (Offline /Online Relocation of Bitstreams) which helps us to accelerate the PBR considerably. In this paper, we compare the developed tool to others in previous works, specifically in the context of many-core applications; we give a particular importance to the reduction in the relocation time, which must to increase the time overhead already incurred by using partial reconfiguration. In this paper, we show how the tool has been used in this context, and a comparative analysis is detailed to highlight the significant relocation speedups that might help in making the relocation process more amenable.

The line of sight (LOS) rate is a parameter that is needed to calculate the acceleration applied to missiles by the proportional guidance laws in order to hit the target. This rate is usually measured using gimbaled seekers. However, if the type of missile seeker be strap down, the LOS rate must be calculated from deriving the missile's seeker output angles or estimation methodes. The derivation method is not desirable due to the noisy output of the seekers and low pass filters are needed to achieve an acceptable output, which will cause a lag in the guidance loop. In this paper, a discrete time extended state observers will be designed to estimate the LOS rate. The advantage of the time discontinuity of the observer is that issues related to the implementation of the observer on the processors, such as the choice of sampling time, considered from the design level and examined in computer simulation.

Os protocolos de roteamento, em caso de falhas em backbones mais velozes, geralmente não obtêm nova rota em tempo hábil. Eles precisam desde centenas de milissegundos até vários segundos para convergir. Durante esse tempo, a rede fica instável, realizando um processo de encaminhamento errado, com altas taxas de pacotes perdidos. Este trabalho propõe uma abordagem de cálculo pró-ativo de caminhos emergenciais rápidos para auxiliar os protocolos de roteamento a contornar falhas. Uma avaliação desses caminhos foi realizada em uma representação de topologia real. Nesta avaliação os caminhos apresentam-se menores que as outras abordagens e ocupam menos informações extras adicionadas na base de encaminhamento por roteador.

The objective of this research is to present the use of blockchain technology, the internet of things and fog computing to develop the potential of school management for smart education. By using the blockchain to record and store various pieces of information the organization will create credibility of administrative data in all departments and will reduce corruption. Data can be examined transparently, especially the financial and budget management and procurement of durable articles. Regarding the academic work and registration, it can be used to store learners' information, educational history, information of enrollment, academic results, and participation in the various activities of the educational institutions. It can create credibility in the management of information about content, learning and ability assessment results that students receive, and these can be recorded and stored in a blockchain that can be safely distributed. In addition, IoT and fog computing are inte...

This paper describes the architecture and mechanisms proposed in the context of the DFT4FTT project for implementing Adaptive Distributed Embedded Systems (ADESs), that is, distributed systems with real-time, dependability and adaptivity requirements. The focus is on the reconfiguration strategies that allow, not only to change the system behaviour, but to improve its tolerance to permanent hardware faults.

Delay tolerant networks (DTNs) are a type of mobile ad hoc network without the infrastructure in which a complete path from a source node to a destination does not exist always; so routing is the most important challenge in these networks. In recent years many routing methods in delay tolerant networks have been proposed. In previous methods, the copies were blindly forwarded to mobile nodes; finally, it caused a reduction in delivery rate and wasting of network resources. So it can be said choosing an appropriate relay node is an important challenge. In this paper, a novel Relay Node Selection by Adaptive Neuro-Fuzzy Inference System (SR-ANFIS) is proposed to improve the Delivery Ratio. In order to calculate the Chance of Receiving (CR), the parameters, Encounter Frequent (EF) to the destination, Selfishness Measure(SM), Closeness-Centrality (CC), Reach-Centrality (RC) are used as inputs of Adaptive Neuro-Fuzzy Inference System(ANFIS). Simulation results illustrate that the SR-ANFI...

Delay tolerant networks (DTNs) are a type of mobile ad hoc network without the infrastructure in which a complete path from a source node to a destination does not exist always; so routing is the most important challenge in these networks. In recent years many routing methods in delay tolerant networks have been proposed. In previous methods, the copies were blindly forwarded to mobile nodes; finally, it caused a reduction in delivery rate and wasting of network resources. So it can be said choosing an appropriate relay node is an important challenge. In this paper, a novel Relay Node Selection by Adaptive Neuro-Fuzzy Inference System (SR-ANFIS) is proposed to improve the Delivery Ratio. In order to calculate the Chance of Receiving (CR), the parameters, Encounter Frequent (EF) to the destination, Selfishness Measure(SM), Closeness-Centrality (CC), Reach-Centrality (RC) are used as inputs of Adaptive Neuro-Fuzzy Inference System(ANFIS). Simulation results illustrate that the SR-ANFIS achieves better results in delivery ratio, delivery latency, message drop, overhead ratio and hop count than other exiting DTN routings.

1 III-LIDI, Facultad de Informática, UNLP Calle 50 y 120, 1900 La Plata (Buenos Aires), Argentina {dmontezanti, erucci, mnaiouf, degiusti}@lidi.info.unlp.edu.ar 2 Departamento de Arquitectura de Computadoras y Sistemas Operativos, UAB Campus UAB, Edifici Q, 08193 Bellaterra (Barcelona), Spain {dolores.rexachs, emilio.luque}@uab.es 3 Consejo Nacional de Investigaciones Científicas y Tecnológicas 4 Instituto de Ingeniería y Agronomía, UNAJ Av. Calchaquí 6200, 1888 Florencio Varela (Buenos Aires), Argentina

In this paper, a novel voter design is presented which allows the voting of asynchronous network streams in flow-controlled networks. The voter synchronises incoming data streams automatically and is able to handle failure modes that typically occur in streaming applications. The voter degrades to a comparator if one of the redundant channels has failed and reintegrates the channels once they are functional again. While the voter is mainly intended to be connected to a routing switch of the network, it also comprises a broadcast mechanism that enables a stand-alone operation. The design has been successfully implemented in hardware and evaluated by means of fault injection experiments.

Reliability is one of the major issues with wireless networks. Failure in multiple radio channels often lead to poor communication even complete disruption in services. Increasing reliability of a network may point to the requirement of multiple paths between two terminals in the network. Hence, a link fault tolerant network design with low cost is important. Fault tolerance of a network is defined as the ability of the network to endure any link or node failure and cater uninterrupted connection for all services. The paper presents a technique to counter the issue of fault tolerance in a wireless mesh network (with static subscriber stations) so that it can sustain malfunction in multiple radio channels and optimize the spectrum usage. A K-fault tolerant network has at least K+1 number of distinct routes between two nodes. So, given a set of nodes and the cost of links there is a need to design a network assigning minimal number of links satisfying some specified connectivity requirements between a pair of terminals.

We address the problem of minimizing the I/O needed to recover from disk failures in erasure-coded storage systems. The principal result is an algorithm that finds the optimal I/O recovery from an arbitrary number of disk failures for any XOR-based erasure code. We also describe a family of codes with high-fault tolerance and low recovery I/O, eg one instance tolerates up to 11 failures and recovers a lost block in 4 I/Os. While we have determined I/O optimal recovery for any given code, it remains an open problem to identify ...

The study has been approved by the local ethics committee. The anonymized data and analysis scripts are available at: https://osf.io/ja2x9/?view_only=64d48f8e309747158f435b825428a0ed There is no conflict of interest to disclose. Research Highlights • Children recognize emotions in masked faces worse than faces wearing nothing or sunglasses. • The longer the duration of exposure to individuals wearing masks, the better children's emotion recognition in faces, including ones wearing no cover. • Exposure to adults wearing masks impairs children's emotion recognition in the short run but benefits it in the long run.

This work was supported under Grants for Brazilian PhD students with Coordination for the Improvement of Higher Education Personnel (CAPES). ABSTRACT Recently, the widespread use of Network Function Virtualization (NFV) has meant a significant shift in communication and network cloud-based services. NFV increases network function, allocation, and flexibility, for the implementation of new network services, The benefits from optimizing resource allocation in NFV data center include automation of the operational processes, reducing the operational efforts, and lowering capital costs. Despite being a hot topic, NFV data centers are still in their early stages. In this sense, there are some aspects involved in the current NFV implementations that required further investigation, such as performance evaluation and managemen. This paper presents an in-depth analysis of NFV applications in data center. Therefore, a Systematic Literature Review (SLR) was conducted aimed at studying and synthesizing the available works in the NFV state-of-the-art. Consequently, about 1,408 papers have been analyzed and filtered, evidencing a total of 65 relevant studies. This paper documents the relevance of the 65 papers, as well as provides an indepth insight into the primary open research questions concerning NFV architecture. In particular, highlighting the need for consolidating the integration of NFV in data centers by solving problems related to performance, dependability, resource allocation, cost, management, and resource interoperability. Based on the conducted SLR, several research gaps and open challenges have been identified, allowing the authors to provide new propositions and suggested future research avenues. Finally, the obtained results have shown that there is a strong need for further collaboration between academia and industry to conduct quality research and advance NFV practical implementations. INDEX TERMS Network function virtualization (NFV), software defined networking (SDN), cloud computing, data center, service function chain (SFC), performance evaluation.