HYSTERY: a hybrid scheduling and mapping approach to optimize temperature,energy consumption and lifetime reliability of heterogeneous multiprocessor systems

In this paper, a hybrid scheduling and mapping approach to jointly optimize performance, lifetime reliability, energy consumption and temperature of heterogeneous multiprocessor systems on chip (MPSoCs), called “HYSTERY,” is proposed. Due to the growth of dynamic behavior in modern applications of embedded systems, along with necessity of performing complicated computations to jointly optimize the main design challenges of MPSoCs, we propose a hybrid scheduling approach in this paper. The proposed approach deals with the optimization of the mentioned design challenges at the design-time through solving an optimization problem and considering load balancing in task assignment. Moreover, at the runtime, the derived static solution is applied to the system and the design metrics monitored periodically and controlled, if required, to adapt the static scheduling decisions at the runtime. Several experiments with synthetic and real-life applications demonstrate that the proposed approach can effectively optimize the design challenges and manage dynamism of execution environment. In comparison with the uncontrolled runtime scheduling approach, HYSTERY shows 20% improvement in temperature averagely, which subsequently enhance lifetime reliability and power consumption. Furthermore, HYSTERY improves the main design parameters of MPSOCs about 21% in average compared to the existing scheduling approaches.     

A constraint programming model for the scheduling of JIT cross-docking systems with preemption

In this paper, a scheduling problem of minimizing the total of the earliness, tardiness and the number of preemption for the outbound trucks on a cross-dock system is considered. This problem, which is known to be NP-hard, is compatible with the concepts of just-in-time (JIT) production and supply chain management. A new multi-criteria model, with non-linear terms and integer variables, which cannot be solved efficiently for large sized problems, is proposed. This paper also shows how to map a JIT cross-dock model to a constraint satisfaction problem (CSP) and integer programming (IP). To solve the model for real size applications, a genetic algorithm (GA) is applied. Finally, a computational experiment is carried out to analyze the performances of CSP, GA and IP models with respect to modeling capability, solution quality and time.     

Cache vulnerability mitigation using an adaptive cache coherence protocol

This paper proposes an adaptive cache coherence protocol to improve the reliability of caches against soft errors in shared-memory multi-core processors. The proposed protocol is conducted based-on a comprehensive study and analysis intended to determine the effects of cache coherence protocols on the characteristics of cache memories. The outcomes of this analysis indicate that differences in handling dirty data items play an important role to make distinction in favor of or against a cache coherence protocol. Based on the primary results, the proposed protocol tries to enhance the reliability of caches by means of sharing management. Sharing is dynamically adjusted according to the operational mode of CPU. The experimental results show that proposed protocol leads to about 16 % improvements in MTTF, with no performance degradation and with negligible bandwidth and cache energy consumption overheads compared to previous works.     

Investigating liquid fronts during spontaneous imbibition of liquids in industrial wicks. Part I: Experimental studies

A large set of industrial wicks made from sintered polymer beads and fibrous materials were studied. Three types of liquid fronts were observed: sharp, semi-sharp, and diffuse. The bead-like microstructure with lower porosity is found to support sharp fronts, while the aligned-fiber microstructure with higher porosities leads to a smudging/diffusing of the fronts. The previously developed sharp-front model is found to predict the front height as a function of time quite well in the sintered-bead wicks and the two “semi-sharp” fibrous wicks. The liquid-front height calculated from the liquid mass-gain data was validated through visual observations for all but the two fibrous wicks generating the diffuse fronts. These latter cases, observed to start off as a sharp fronts, faded with time.     

MSDP with ACO: A maximal SRLG disjoint routing algorithm based on ant colony optimization

Failure resilience is a desired feature in communication networks, and different methods can be considered in order to achieve this feature. One of these methods is diverse Routing. In this paper, we are going to suggest a sort of diverse routing algorithm, which can find two maximal shared risk link group (SRLG) disjoint paths between a source and a destination node. This algorithm is based on ant colony optimization algorithm, which consists of three parts. These parts are graph transformation technique, finding two maximal edge-disjoint routes and reverse transformation. The final routes are always maximal SRLG disjoint. Simulation results show the efficiency of the proposed method.     

Identification of the linear parts of nonlinear systems for fuzzy modeling

In direct approach to fuzzy modeling, structure identification is one of the most critical tasks. In modeling the nonlinear system, this fact is more crucial. In this paper, a new hybrid method is proposed to cluster the data located in the linear parts on the nonlinear systems. The proposed method can partition the input–output data in two groups: data located in the linear parts and data in the extrema. It is shown that the first group of data is suitable to be clustered by Fuzzy C-Regression Model (FCRM) clustering algorithm and the second group by Fuzzy C-Means (FCM). Then, based on the above findings, a new hybrid clustering algorithm is proposed. Finally, the proposed approach is tested and validated by several numerical examples of nonlinear functions.     

Flow along and across glass‐fiber wicks: Testing of permeability models through experiments and simulations

A rigorous test of important theoretical models for permeability of glass‐fiber wicks, backed by numerical simulations, is conducted using a novel small‐scale experiment. The models include those for flow along and across aligned fibers and for flow through random fibers. The domains for numerical simulations were created by randomly distributed parallel fibers in a cube‐like unit‐cell using Geodict. Two separate simulations were considered: (1) Stokes‐flow solution using GeoDict, (2) Whitaker's closure‐formulation solution using COMSOL. The falling‐head parameter was adapted to measure the permeability along and across the fibers. Multiple measurements were conducted for each of the wicks to establish repeatability and estimate scatter. The permeabilities obtained through experiments matched with those from the theoretical and numerical methods. But numerical permeabilities for the longitudinal flow were exceptionally accurate. Also, the specialized models for longitudinal and transverse flows were more accurate than the random‐fiber models. © 2018 American Institute of Chemical Engineers AIChE J, 64: 3491–3501, 2018     

In Vitro Propagation of XXY Undifferentiated Mouse Spermatogonia: Model for Fertility Preservation in Klinefelter Syndrome Patients

Klinefelter syndrome (KS) is characterized by a masculine phenotype, supernumerary sex chromosomes (usually XXY), and spermatogonial stem cell (SSC) loss in their early life. Affecting 1 out of every 650 males born, KS is the most common genetic cause of male infertility, and new fertility preservation strategies are critically important for these patients. In this study, testes from 41, XXY prepubertal (3-day-old) mice were frozen-thawed. Isolated testicular cells were cultured and characterized by qPCR, digital PCR, and flow cytometry analyses. We demonstrated that SSCs survived and were able to be propagated with testicular somatic cells in culture for up to 120 days. DNA fluorescent in situ hybridization (FISH) showed the presence of XXY spermatogonia at the beginning of the culture and a variety of propagated XY, XX, and XXY spermatogonia at the end of the culture. These data provide the first evidence that an extra sex chromosome was lost during innate SSC culture, a crucial finding in treating KS patients for preserving and propagating SSCs for future sperm production, either in vitro or in vivo. This in vitro propagation system can be translated to clinical fertility preservation for KS patients.     

Type-2 fuzzy hybrid expert system for prediction of tardiness in scheduling of steel continuous casting process

This paper addresses an interval type-2 fuzzy (IT2F) hybrid expert system in order to predict the amount of tardiness where tardiness variables are represented by interval type-2 membership functions. For this purpose, IT2F disjunctive normal forms and fuzzy conjunctive normal forms are utilized in the inference engine. The main contribution of this paper is to present the IT2F hybrid expert system, which is the combination of the Mamdani and Sugeno methods. In order to predict the future amount of tardiness for continuous casting operation in a steel company in Canada, an autoregressive moving average model is used in the consequents of the rules. Parameters of the system are tuned by applying Adaptive-Network-Based Fuzzy Inference System. This method is compared with IT2F Takagi–Sugeno–Kang method in MATLAB, multiple-regression, and two other Type-1 fuzzy methods in literature. The results of computing the mean square error of these methods show that our proposed method has less error and high accuracy in comparison with other methods.