14,613 research outputs found
Survey on Grid Resource Allocation Mechanisms
Grid is a distributed high performance computing paradigm that offers various types of resources (like computing, storage, communication) to resource-intensive user tasks. These tasks are scheduled to allocate available Grid resources efficiently to achieve high system throughput and to satisfy user requirements. The task scheduling problem has become more complex with the ever increasing size of Grid systems. Even though selecting an efficient resource allocation strategy for a particular task helps in obtaining a desired level of service, researchers still face difficulties in choosing a suitable technique from a plethora of existing methods in literature. In this paper, we explore and discuss existing resource allocation mechanisms for resource allocation problems employed in Grid systems. The work comprehensively surveys Gird resource allocation mechanisms for different architectures (centralized, distributed, static or dynamic). The paper also compares these resource allocation mechanisms based on their common features such as time complexity, searching mechanism, allocation strategy, optimality, operational environment and objective function they adopt for solving computing- and data-intensive applications. The comprehensive analysis of cutting-edge research in the Grid domain presented in this work provides readers with an understanding of essential concepts of resource allocation mechanisms in Grid systems and helps them identify important and outstanding issues for further investigation. It also helps readers to choose the most appropriate mechanism for a given system/application
Feasibility Analysis and Design of Real-Time Systems
针对周期性任务系统,主要是静态优先级调度策略的在线分析,本文提出了一组可调度判定算法。一个是增强的时间需求分析(ETDA),相比经典的时间需求分析(TDA),它精简了判定任务可调度性需要考察的调度点数目。另一个是混合可调度判定(HT),这是一种严格的可调度判定条件,它将已有的充分条件和充要条件结合起来,大大减少了分析时间。为进一步减少分析时间,本文还展示了一个有希望的方法:在进行可调度判定时,将现有的最高优先级优先策略替换为最低优先级优先(LPF)策略。
我们也考察了任务截止期和谐(即复合截止期)的效果,已有多个严格判定条件与此相关。我们提出的第一个判定条件主要关注如何在单个调度点上判定任务的可行性,而提出的第二个判定条件给出了一个基于CPU 利用率的严格判定算法,该算法针对和谐任务系统,其时间复杂度为O(n)。
现有的调度技术大多假设系统提供的优先级个数是不受限制的。然而,基于多种因素如经济等的考虑,大量的系统仅支持有限的优先级,相比优先级个数不受限制的情况,这方面的研究还很有限。为了适应上述应用的需求,转换技术用于将在优先级个数不受限制下可调度的任务集转换为在有限优先级下可调度的任务集,然而这种转换需要付出代价,新得到的任务集会变得不可调度,因此需要研究相应的转换技术,使得原来可调度的任务集在有限优先级下仍旧可以确保其可调度性。
节约能源是当今实时嵌入式系统设计的一个关键技术,处理器消耗了整个系统的很大一部分能源。一方面,最新器件及其复杂需求导致了对能源的大量需求,另一方面,电池技术的改进进展缓慢。由于近期相关技术很难有突破,所以目前研究重点是如何有效地利用电池能源。大量研究集中于利用动态电压调整技术,而其代价是降低了系统的响应性。但是在最新的设备中,尤其是交互式手持设备中,响应性要比节约能源更重要。因此,有效的调度策略应当同时考虑系统的响应性和节约能源。除了对动态电压调整技术在实时调度理论中的应用进行了综述,本文也提出了一个解决方法,用于处理混合负载的情形,使得系统的性能可以得到保证。
周期性任务系统的可调度性对任务参数是敏感的,系统设计师通过调整多个参数,使得系统的某个目标函数最优,如处理器利用率最大,或者能源消耗最少等。这些参数主要包括任务周期,截止期和执行时间。任务周期通常取决于系统需求,而截止期和执行时间可以被修改以便改善系统性能。在基于优先级调度的系统中,这种敏感性分析集中于改变任务执行时间和截止期上,然而迄今为止还没有最优的解决方法。我们将给定的一串由“逻辑或”连接的不等式,转换为一个独立的不等式,然后用这个不等式作为任务可调度的约束条件。这个不等式可以通过非线性规划的方法解决,以便可以设计出最大化系统目标函数如系统利用率、优化能源的方案。这同时也提供了一个通过改变任务执行时间或者处理器执行速度,将不可调度的任务集转换为可调度任务集的方法。This work presents a collection of feasibility conditions for the online analysis of periodic task systems, mainly, under fixed priority scheduling policy. The first proposed test called enhanced time demand analysis (ETDA) is an efficient algorithm that confines testing schedulability of task to a reduced set of actual points as compared to the classic time demand analysis (TDA). The hybrid test (HT) is another exact condition constituted by combining sufficient condition and necessary and sufficient condition, taken from existing literature, which greatly reduces the analysis time of
periodic task sets. To further reduce the analysis time of these systems a promising alternative is shown to be the replacement of the current highest priority first approach with lowest priority first(LPF) order.
The effect of making the task deadlines harmonic is also observed and a couple of exact conditions are evolved with this formulation. The first condition is focusing on testing task feasibility at a single scheduling point, while the second test provides a utilization based exact test with complexity. Both are intended for systems having harmonic deadlines.
Most of the current scheduling techniques are based on theassumption that the number of priority levels supported by the underlying hardware is infinite. However, due to many considerations such as economic, enormous systems do exist, where the number of priority levels is limited and this area of limited priority remains relatively unexplored, in contrast to unlimited counter part. In order to accommodate such systems, transformation mechanism are used to convert an unlimited priority feasible task system into the one that can be executed with limited priority levels, however this
transformation comes at the price; the newly created set might become infeasible. Care is required for such transformation so that the feasibility of the original set should be guaranteed even with limited priority levels by acquiring the lower number of priority levels required. The mechanism is explained in detail in this work and the feasibility of the unlimited priority feasible task set is kept intact with limited .
Power consumption is an important issue in the design of latest real-time embedded systems, where the core processor consumes a large amount of the total system energy. On one front, the complex requirements of latest devices make them power hungry while on the other front the improvement in battery technologies is prohibited due to its fundamental limitations. Since no breakthrough is expected in near future, the focus is shifted to utilizing the battery power more efficiently. Much research is focused on the power reduction of the current dynamic voltage scaling enabled
processor at the expense of system responsiveness. In latest devices, especially in interactive hand held devices, responsiveness is of higher importance than energy saving. Hence, a useful scheduling policy should account for system responsiveness as well as power reduction. A solution is also proposed for handling mixed workload such that system performance is bounded by its deadline, in addition to a survey of DVS techniques into real-time scheduling theory.
In the last part of the thesis, we endeavor to present the concept of generalized bound of task schedulability to chalk out the specification requirements of a system under investigation in a formal way. Since schedulability of a periodic system is sensitive to task parameter, multiple parameters are exploited by the system designer at design time for maximizing some objective function such as increasing processor utilization or reducing the power consumptions of the systems. These parameters include task period, deadline and execution times. The task periods are usually set by the system requirements, but deadline and computation times can be modified in order to improve system performance. Under priority based scheduling, such sensitivity analysis has focused on changing the task execution times and deadlines, however no optimal solution is known as yet, prior to this work. We transform the given list of inequalities linked through logical OR conditions into a single
inequality. This inequality becomes a constraint of task schedulability, which can be solved with nonlinear programming techniques for obtaining optimal task execution times that can be applied at design time for minimizing some objective function such as energy consumption or system utilization. The generalized bound provides the facility of finding the optimal values for execution times or processor speed for converting a non-feasible task set into a feasible one
Quantum computing research in medical sciences
With the emergence of ever-improving quantum computers, technology is making its way to revolutionize many fields, and the medical sector is no exception. Recent efforts have explored applications of quantum computing in areas such as drug discovery, patient privacy, and information security. It is expected that, with improved and stable quantum computing technologies, the medical sector will benefit significantly in many areas, including efficient patient care, reduced clinical trial durations, enhanced imaging technologies, and post-quantum cryptography, to name a few.In this work, we highlight recent advancements in the medical sector driven by quantum computing, encompassing computation, optimization, security, machine learning, data processing, simulation, and healthcare perspectives. We also discuss the limitations of current technologies, and the challenges associated with the quantum computing revolution
Etude éxpérimentale et numérique des effets de charge éléctrostatique dans les lits fluidisés gaz-solides
Les lits fluidisés gaz-solides sont largement utilisés dans les procédés industriels pour l'énergie tels que la combustion, la polymérisation, les récepteurs solaires, la gazéification de la biomasse et le raffinage du pétrole. Dans ces procédés, les forces électrostatiques ont été généralement négligées. Cependant, le phénomène présente des problèmes majeurs tels que l'encrassement des murs, la défluidisation, les étincelles, les explosions de poussière et parfois des incendies. A l'échelle moléculaire, le contact entre deux particules génère un transfert d'électrons/ions, induisant une charge sur chaque particule. Par conséquent, le gaz environnant transporte un champ électrique, ce qui produit une force supplémentaire connue sous le nom de force de Lorentz. Le phénomène dépend des propriétés des matériaux et les conditions opératoires. Plusieurs travaux dans la littérature ont étudié l'effet de chaque paramètre. Cependant, il y a un manque d'étude combinant à la fois des mesures expérimentales et la modélisation théorique avec des simulations numériques. La présente étude s'inscrit donc dans ce contexte. Elle fait partie de la Chaire d'attractivité BIREM (BIological, REacting, Multiphase flows) attribuée au Professeur Rodney Fox, soutenue financièrement par l'Université de Toulouse, dans le cadre du programme de recherche IDEX. Le projet est hébergé par la Fédération de recherche FERMaT. Dans ce travail, des expériences ont été réalisées sur différentes distributions granulométriques, différents matériaux et différentes conditions opératoires. Le dispositif expérimental, conçu et réalisé lors de cette thèse, consiste en une colonne en plexiglas de 1 m de hauteur et 0,1 m de diamètre. La technique de mesure utilisée est une coupe de Faraday reliée à un électromètre. Les résultats montrent deux catégories de particules : les "dropped" particules qui tombent immédiatement après l'ouverture de la vanne et les "wall" particules qui collent à la paroi. Les résultats ne montrent aucun effet de l'humidité relative sur la vitesse minimale de fluidization (Umf). L'évolution de la charge nette du lit en fonction du temps de fluidisation a montré une tendance exponentielle qui atteint une valeur d'équilibre pour les deux catégories. Les "wall" ont été chargées de 250 à 450 fois plus que les "dropped". La charge diminue en augmentant l'humidité relative. Les petites particules ont présenté une charge positive alors que toutes les autres distributions étaient chargées négativement. La charge d'équilibre des "dropped" n'a pas été influencée par l'augmentation de la vitesse alors que le temps d'équilibre a été légèrement augmenté. La charge d'équilibre des "wall" a été significativement augmentée. D'autre part, le travail numérique a modélisé la force de Lorentz dans une approche eulérienne. Les simulations ont été réalisées avec NEPTUNE_CFD. Les murs étaient supposés mis à la terre. Le modèle a été validé sur plusieurs cas de test. Par la suite, un modèle de tribélectrification (génération de charge) a été développé dans une approche eulérienne en s'inspirant d'analogie avec des modèles dans la littérature. Les conditions aux limites ont été élaborées en utilisant des hypothèses moins restrictives. Une estimation des temps caractéristiques de génération et de diffusion des charges a été réalisée, montrant que l'échelle de temps est très élevée (plusieurs jours) et ne correspond pas aux résultats expérimentaux (15 à 20 min). Un coefficient correcteur a été proposé pour être en accord aux résultats expérimentaux. De plus, des simulations numériques sur un lit fluidisé ont été réalisées. Le régime permanent a été considéré atteint et la charge d'équilibre a été imposée sur les particules. Les simulations visaient à comparer le cas sans et avec charge. L'effet de la charge sur les propriétés d'écoulement a été mis en évidence. Ces résultats ont mis en évidence l'effet crucial de l'électrostatique sur la suspension fluidisée gaz-particules.Gas-solid fluidized beds are widely used in industrial processes for energy such as chemical looping combustion, catalytic polymerization, solar receiver, biomass gasification and petroleum refinery. In all these processes, electrostatic forces were usually neglected. In polyolefin industry, the phenomena of electrostatic charges presents a major issues including wall fouling. At a molecular scale, the contact between two particles generates a transfer of electrons/ions, inducing a charge on each particle. As a result, the surrounding gas carries an electric field, resulting in an additional force to the momentum equation known as Lorentz force. The phenomenon depend on many parameters, including materials properties and operating conditions. Several works in literature studied the effect of each parameter. However, there is a lack of research projects which combine both experimental study and theoretical modelling with numerical simulation. Thus, this study falls within the context. It is a part of the Attractivity Chair BIREM (BIological, REacting, Multiphase flows) attributed to Professor Rodney Fox, financially supported by the University of Toulouse, in the framework of the IDEX research program. The project is hosted by the research federation FERMaT. The study aims to combine both experimental study in a lab-scale pilot and the numerical modelling in order to represent the electrostatic force in CFD code through the Euler-Euler formalism. In this work, experiments were performed on different particles size distributions, different materials and different operating conditions. The experimental setup, designed and built during the PhD thesis, consisted of a 1 m height and 0.1 m inner diameter plexiglass column. The measuring technique used for charge is a Faraday cup connected to an electrometer. Results shows two categories of particles: dropped particles that falls immediately after opening the valve and wall particles that stick to the wall. Results show no effect of relative humidity on minimum fluidization velocity (Umf). The evolution of the net charge versus fluidization time showed an exponential trend that reached an equilibrium value for both categories. Wall particles were charged 250 to 450 times than dropped ones. The net charge was decreased by increasing relative humidity. Small particles showed a positive charge whereas all other PSDs were negatively charged. The equilibrium charge of dropped particles did not show significant changes when increasing gas velocity whereas the time needed to reach equilibrium was slightly increased. Wall particles equilibrium charge was significantly increased. On the other hand, the numerical work built an electrostatic model for the Lorentz force in an Eulerian approach. Simulations were carried out with a software called NEPTUNE_CFD. The walls were assumed to be grounded. The model was tested with several test cases. After that, a tribocharging model was developed to take into account the charge generation and transfer. The model was inspired from previous works and transposed into an Eulerian approach. The wall boundary conditions were developed in this study by using less restrictive hypothesis. An estimation of the characteristic times of both charge generation and diffusion was performed, showing that the timescale is very high (several days) and does not match with experimental findings (15 to 20 min). A corrective coefficient was proposed to match with experimental results. Moreover, numerical simulations on a fluidized bed with the same dimensions as the experimental pilot were carried out. In these simulations, the permanent regime was considered. The equilibrium charge was prescribed on the particles. Simulations aimed to compare the no-charge case and the charged case. The effect of the charge on the flow properties were highlighted. These results pointed out the crucial effect of the electrostatic on the gas-particle fluidized suspension
Experimental and numerical investigation of electrostatic effects in gas-solid fluidized beds
Gas-solid fluidized beds are widely used in industrial processes for energy such as chemical looping combustion, catalytic polymerization, solar receiver, biomass gasification and petroleum refinery. In all these processes, electrostatic forces were usually neglected. In polyolefin industry, the phenomena of electrostatic charges presents a major issues including wall fouling. At a molecular scale, the contact between two particles generates a transfer of electrons/ions, inducing a charge on each particle. As a result, the surrounding gas carries an electric field, resulting in an additional force to the momentum equation known as Lorentz force. The phenomenon depend on many parameters, including materials properties and operating conditions. Several works in literature studied the effect of each parameter. However, there is a lack of research projects which combine both experimental study and theoretical modelling with numerical simulation. Thus, this study falls within the context. It is a part of the Attractivity Chair BIREM (BIological, REacting, Multiphase flows) attributed to Professor Rodney Fox, financially supported by the University of Toulouse, in the framework of the IDEX research program. The project is hosted by the research federation FERMaT. The study aims to combine both experimental study in a lab-scale pilot and the numerical modelling in order to represent the electrostatic force in CFD code through the Euler-Euler formalism. In this work, experiments were performed on different particles size distributions, different materials and different operating conditions. The experimental setup, designed and built during the PhD thesis, consisted of a 1 m height and 0.1 m inner diameter plexiglass column. The measuring technique used for charge is a Faraday cup connected to an electrometer. Results shows two categories of particles: dropped particles that falls immediately after opening the valve and wall particles that stick to the wall. Results show no effect of relative humidity on minimum fluidization velocity (Umf). The evolution of the net charge versus fluidization time showed an exponential trend that reached an equilibrium value for both categories. Wall particles were charged 250 to 450 times than dropped ones. The net charge was decreased by increasing relative humidity. Small particles showed a positive charge whereas all other PSDs were negatively charged. The equilibrium charge of dropped particles did not show significant changes when increasing gas velocity whereas the time needed to reach equilibrium was slightly increased. Wall particles equilibrium charge was significantly increased. On the other hand, the numerical work built an electrostatic model for the Lorentz force in an Eulerian approach. Simulations were carried out with a software called NEPTUNE_CFD. The walls were assumed to be grounded. The model was tested with several test cases. After that, a tribocharging model was developed to take into account the charge generation and transfer. The model was inspired from previous works and transposed into an Eulerian approach. The wall boundary conditions were developed in this study by using less restrictive hypothesis. An estimation of the characteristic times of both charge generation and diffusion was performed, showing that the timescale is very high (several days) and does not match with experimental findings (15 to 20 min). A corrective coefficient was proposed to match with experimental results. Moreover, numerical simulations on a fluidized bed with the same dimensions as the experimental pilot were carried out. In these simulations, the permanent regime was considered. The equilibrium charge was prescribed on the particles. Simulations aimed to compare the no-charge case and the charged case. The effect of the charge on the flow properties were highlighted. These results pointed out the crucial effect of the electrostatic on the gas-particle fluidized suspension
Author Correction: Human fingerprint in global weather
In the version of this News & Views originally published, the ref. 5 author surnames Meihnausen, Fisher and Szekely were spelled incorrectly; they should have been spelled Meinshausen, Fischer and Székely, respectively. This has now been corrected. © 2020, Springer Nature Limited.11Nsciessciscopu
enhancing feasibility analysis of ieee 802.5 token ring
IFIP TC6 WG 6 8, IEEE, STTTelkoms Indonesia, Inst Teknol Sepuluh Nopember Indonesia, IFIP TC WG6 6, IEEE ComSoc, IEEE ComSoc Wireless Commun Tech Comm, IEEE Commun Soc, Asian Pacific, IEEE ComSoc Indonesian Chapter, IEEE Indonesian Sect, IFIPSchedulability analysis of real-time system has been a central focus of research in scheduling theory and a remarkable progress is made in recent years. This progress provides the opportunity to integrate these state of the art results into r
IoT Based Smart Water Quality Monitoring: Recent Techniques, Trends and Challenges for Domestic Applications
Safe water is becoming a scarce resource, due to the combined effects of increased population, pollution, and climate changes. Water quality monitoring is thus paramount, especially for domestic water. Traditionally used laboratory-based testing approaches are manual, costly, time consuming, and lack real-time feedback. Recently developed systems utilizing wireless sensor network (WSN) technology have reported weaknesses in energy management, data security, and communication coverage. Due to the recent advances in Internet-of-Things (IoT) that can be applied in the development of more efficient, secure, and cheaper systems with real-time capabilities, we present here a survey aimed at summarizing the current state of the art regarding IoT based smart water quality monitoring systems (IoT-WQMS) especially dedicated for domestic applications. In brief, this study probes into common water-quality monitoring (WQM) parameters, their safe-limits for drinking water, related smart sensors, critical review, and ratification of contemporary IoT-WQMS via a proposed empirical metric, analysis, and discussion and, finally, design recommendations for an efficient system. No doubt, this study will benefit the developing field of smart homes, offices, and cities
- …
