A survey on resource allocation in high performance distributed computing systems

An efficient resource allocation is a fundamental requirement in high performance computing (HPC) systems. Many projects are dedicated to large-scale distributed computing systems that have designed and developed resource allocation mechanisms with a variety of architectures and services. In our study, through analysis, a comprehensive survey for describing resource allocation in various HPCs is reported. The aim of the work is to aggregate under a joint framework, the existing solutions for HPC to provide a thorough analysis and characteristics of the resource management and allocation strategies. Resource allocation mechanisms and strategies play a vital role towards the performance improvement of all the HPCs classifications. Therefore, a comprehensive discussion of widely used resource allocation strategies deployed in HPC environment is required, which is one of the motivations of this survey. Moreover, we have classified the HPC systems into three broad categories, namely: (a) cluster, (b) grid, and (c) cloud systems and define the characteristics of each class by extracting sets of common attributes. All of the aforementioned systems are cataloged into pure software and hybrid/hardware solutions. The system classification is used to identify approaches followed by the implementation of existing resource allocation strategies that are widely presented in the literature.     

Instrumentation and computer capabilities for improving sodar data acquisition

A computer program has been developed to exploit the multimedia capabilities of a personal computer for a new design of sodar (sonic detection and ranging) data acquisition and control system with minimized hardware elements. Advantages include trouble-free, cost-effective and user-friendly sodar data acquisition using any standard computer. The new design overcomes limitations due to using an add-on data acquisition card with conventional computer-controlled sodar. The data can be processed to produce online display of the dynamics of prevailing atmospheric boundary layer thermal structures and inversion/mixing depth for environmental applications.     

The Dependence of the Melting Temperature of Cobalt–Carbon Eutectic on the Morphology of its Microstructure

Fixed points provide a reliable way to realize and verify temperature scales. High-temperature fixed points are being developed based upon alloys, since single-phase materials are impractical to use above the copper freezing point. In particular, eutectic alloys have been shown to be sufficiently reproducible to warrant consideration as a way to significantly improve high-temperature metrology. However, eutectic alloys have certain characteristics requiring that they are used differently from the current ITS-90 fixed points. As their freezing temperature depends on the freezing rate, the melting temperature is preferred, though it has been shown that for some alloys, notably iron–carbon and cobalt–carbon, the apparent melting temperature can depend on the rate of the preceding freeze. This behavior will need to be explained and quantified if such fixed points are to be acceptable. The effect of varying the freezing rate on subsequent melting has been investigated for cobalt–carbon eutectic fixed points. The apparent melting temperature varies by up to 50 mK. Measurements were made of two different fixed-point blackbodies with very similar results. Optical microscopy of samples produced at different freeze rates shows a change in scale of the microstructure. Electron back-scatter diffraction (EBSD) shows evidence of high levels of residual strain in rapidly frozen samples. The effect of annealing on the melting behavior and microstructure has also been investigated. It is suggested that disordered phase boundaries and residual strain lead to changes in the melting behavior as nonequilibrium conditions may lead to a significant level of pre-melting. Whether this actually changes the liquidus temperature, or whether the melting temperature variation is due to the way the melting point is defined, is also discussed. The variation requires consideration if the highest accuracy is to be achieved, and will be a contributory factor to any uncertainty budget.     

Performance Evaluation of a Commercial Polyurethane Coating in Marine Environment

A material evaluation study has been carried out to determine corrosion behavior of a commercial polyurethane coating system (Souplethane 5) in the marine environment. The coating system is solvent free, two-component polyurethane protective coating. The performance of the coating on steel and rebar concrete was evaluated by conducting different types of tests which include atmospheric exposure, immersion in 5% sodium chloride solution, exposure to splash zone in seawater, salt fog, sabkha soil burial, and electrochemical tests, which include potentiodynamic polarization and AC impedance measurements. Uncoated, coated, and coated scribed specimens were used in each study. In general, the coating showed good corrosion resistance in marine environment. However, the coated samples, when subjected to break under applied compressive load, showed partial or complete detachment from the substrate, e.g., steel and rebar concrete. This appears to be the major drawback of the coating while applying on steel and concrete structures.     

Implementation and experimental studies of an adaptive self-optimizing power system stabilizer

This paper describes the implementation and experimental studies of an adaptive self-optimizing pole shifting power system stabilizer. Using an Intel iSBC386/21 single-board computer, the adaptive power system stabilizer has been tested on a physical model of a single-machine infinite-bus power system. Under different operating conditions and disturbances, the behavior of the proposed adaptive stabilizer was investigated. Comparison has also been made to a digital-type conventional fixed-parameter power system stabilizer. Results of the experimental studies show that the proposed adaptive stabilizer outperforms the conventional stabilizer.     

Fatigue delamination growth under cyclic compression in glass/epoxy composite beam/plates

Results are reported on the fatigue growth of internal delaminations in glass/epoxy composite beam/plates subjected to constant amplitude cyclic compression. Because of compressive loading, these structures undergo repeated buckling/unloading of the delaminated layer with a resulting reduction of the interlayer resistance. A noteworthy feature of the problem is that the state of stress near the delamination tip is of mixed mode (I and II). The present combined experimental/analytical investigation for the glass/epoxy composites complements our earlier studies on delamination growth under cyclic compression in unidirectional graphite/epoxy specimens. Several configurations are studied with the delamination located at different depths (through the thickness) and with different applied maximum compressive displacements. The experimental data are correlated with the predictions from a combined delamination buckling/postbuckling and fracture mechanics model. A mode-dependent fatigue delamination growth law is used together with an initial postbuckling solution for the deformation pattern of the delaminated layer and the substrate, which does not impose any restrictive assumptions on the delamination thickness and plate length. The experimental data seem to be adequately correlated with the theory and the fatigue delamination growth is found again to be strongly affected by the relative location of the delamination through the plate thickness. Finally, a comparison of the cyclic growth rate in glass/epoxy specimens with the corresponding one in graphite/epoxy specimens of the same geometry and applied loading shows that the delamination would grow much faster in the graphite/epoxy specimens.     

Effects of passive tilt and submaximal exercise on spectral heart rate variability in ventricular fibrillation patients without significant structural heart disease

It has been shown that tilt and exercise elicit significant changes in autonomic activity in normal subjects and that submaximal exercise causes a greater reduction in heart rate variability (HRV) in animals susceptible to ventricular fibrillation (VF). Whether there is an abnormal HRV response to tilt and exercise in patients at risk of sudden cardiac death (SCD) remains unknown. Short-term HRV before and during passive tilt and exercise was studied in 12 survivors of out-of-hospital cardiac arrest with documented VF and compared with 12 age- and sex-matched normal controls. No patient had significant structural heart disease or left ventricular dysfunction. HRV was computed as total-frequency (TF, 0.01 to 1.00 Hz), low-frequency (LF, 0.04 to 0.15 Hz) and high-frequency (HF, 0.15 to 0.40 Hz) components. There was no significant difference between normal controls and SCD survivors in HRV before or during tilt or submaximal exercise testing. The HF component was significantly decreased during tilt compared with that in the supine position in both normal controls (5.85 +/- 0.61 vs 5.08 +/- 0.95 In(msec2), p = 0.005) and patients (5.58 +/- 1.49 versus 4.74 +/- 1.18 In(msec2), p = 0.003). There was again no significant change in the TF or LF components during tilt in either patients or controls. All frequency components were significantly decreased during submaximal exercise testing in both patients and controls. However, there was no significant difference in any of these tilt- and exercise-induced changes in HRV between normal controls and SCD survivors.(ABSTRACT TRUNCATED AT 250 WORDS)     

Morphological and mechanical studies of surface treated mica reinforced high density polyethylene

Morphological studies of high density polyethylene (HDPE) reinforced by mica flakes has been investigated. The mica flakes were surface treated by silane and titanate coupling agents. Effects of these treatments on the polymer-mica interface is discussed. It is found that surface treatment, particularly silane treated composites, have better adhesion between the reinforcing agent and the polymer matrix. This effect can only be detected when the mica concentration is higher than 20 weight percent. This interfacial adhesion could not be seen across the surface of the sample but only when the measurements were made parallel to the surface.     

Efficient bufferless packet switching on trees and leveled networks

In bufferless networks the packets cannot be buffered while they are in transit; thus, once injected, the packets have to move constantly. Bufferless networks are interesting because they model optical networks. The objective of this work is to demonstrate that efficient bufferless packet switching is achievable in particular, interesting network topologies.     

Dependence of thermal sensitivity of LPFG on waveguide and material parameters

This article demonstrates the effect of waveguide and material parameters on thermal sensitivity trends adopted by different cladding modes based on long-period fiber grating. Three-layer fiber geometry-based mathematical model has been implemented to estimate cladding modes. It is observed that for a cladding mode, the sign and magnitude of thermal sensitivity slope depend upon the designed grating period closer to period at dispersion turn around point. The \(\hbox {LP}_{10}\) and \(\hbox {LP}_{11}\) cladding modes have shown blueshift and maximum thermal sensitivity above all other modes at designed grating periods of 225 and \(195\,\upmu \hbox {m}\), respectively. The material parameter of fiber (thermo-optic coefficient) has also resulted in increment in sensitivity with the increase in difference amid its values for core and cladding region.