Search

It is very crucial to solve the Reynolds equation quickly and accurately using the numerical methods in the research field of fluid lubrication. For the static Reynolds equation of self‐acting gas journal bearings, the typical solution algorithm of the finite difference method is put forward and a new solution algorithm of the finite difference method is proposed. Secondly, the Reynolds equation is solved numerically with the same parameters and the pressure distribution of gas bearings is obtained. Finally, the numerical solution from the new solution algorithm can be obtained with less number of iterations and the less computing time under the different computational grids and bearing numbers. Therefore, the new solution algorithm of the finite difference method is superior to the typical solution algorithm of the finite difference method. [ABSTRACT FROM AUTHOR]

In the ever-evolving landscape of computational grid systems, the meticulous selection of resources tailored to specific tasks is a formidable challenge. This paper introduces an efficient load distribution strategy known as Load Distribution Based Resource Allocation (LDRA), one of the foremost goals is to allocate resources to gain enhanced resource utilization and also try to achieve least possible execution time to fulfil the need for grid systems. A comprehensive performance evaluation unfolds to elevate grid efficiency, pitting LDRA against existing heuristics using the ETC Simulation Benchmark. The study expands further on the real-world dataset from the Gaia Cluster Configurations (https://hpc.uni.lu/systems/gaia/) to verify its significance in the real environment. The LDRA algorithm emerges with superior performance when compared to state-of-the-art such as Max–Min, Opportunistic Load Balancing, AlgHybrid_LB, and Resource Aware Load Balancing for resource utilization, makespan, flowtime, and energy efficiency in the majority of the cases in experimental evaluation. In some cases, the experimental results show that LDRA's usage of the grid resources is remarkable, reaching over 99% in four cases and approaching 98% in two cases of the ETC simulation benchmark. These accomplishments are further mirrored in the evaluation against real datasets, where LDRA's performance among peers is nothing short of exemplary in the cases under study. [ABSTRACT FROM AUTHOR]

Gridlet allocation in a computational grid environment is a major research issue to obtain not only the efficient gridlet allocation technique but also the time needed to obtain the efficient allocation technique. Grid computing networks have various nodes to process user jobs. To achieve the high performance of computational grid, task scheduling is an important issue. The users who are using services of grid systems are more cautious about time to complete their job. Hence, this work concentrates on gridlet allocation method used for time reduction by a genetic algorithm with the MapReduce programming model for independent tasks in computational grid. In computational grid environment, multi-objective problem formulation minimization of makespan and flowtime is considered. In this proposed technique, fitness function formulation for makespan and flowtime has been formulated mathematically. The genetic algorithm with the MapReduce programming model is implemented using MapReduce written in Java and then combined with GridSim. The experimental outcome with regard to time needed, flowtime, and makespan clearly reveals that the genetic algorithm with the MapReduce model effectively optimizes time, makespan, and flowtime in computational grid environment. A comparative study of performance efficiency among genetic algorithm with the MapReduce and sequential genetic algorithm (SGA) and parallel genetic algorithm (PGA) depicts the usefulness of the model. The execution time achieved by GA with the MapReduce model in small grid is 10.48 s, medium grid is 18.76 s, and large grid is 33.73 s. [ABSTRACT FROM AUTHOR]

In this paper, the investigation was performed to determine the effect of leading-edge angle and leading-edge sweep on the aerodynamic coefficients of the projectile geometry and analyze the effect of roll moment on the fins at various operating conditions. A group of four models were considered, standard TTCP with the blunt leading edge and with 45° leading-edge along with modified TTCP with the blunt leading edge along with 30° sweep and with 45° leading-edge along with 30° sweep. The flow field solutions were obtained and considered as a function of roll moment coefficients, which are then compared to other numerical models and experimental results. The standard wrap-around TTCP models were subjected to varying velocities ranging from Mach 1.5 to 2.5. WAFs are considered a choice for spinning tube-launched projectiles because of their high packing factor and instant deployment. The computational grids have been built to accurately reflect the fin edge shape of the experimental model. The significant parameter of the WAF is the rolling moment, that was computed using CFD and compared with available experimental test data.

Generally, the computational grid consists of a large number of computing nodes, some of them are idle due to the uneven geographical distribution of computing requirements. This may cause workload unbalancing problems, which affect the performance of large-scale computational grids. In order to balance the computing requirements and computing nodes, we propose a job scheduling algorithm based on the workload prediction of computing nodes. We first analyze the causes of workload imbalance and the feasibility of reallocating computing resources. Secondly, we design an application and workload-aware scheduling algorithm (AWAS) by combining the previously designed workload prediction model. To reduce the complexity of the AWAS algorithm, we propose a parallel job scheduling method based on computing node workload prediction. The experiments show that the AWAS algorithm can balance the workload among different computing nodes on the real-world dataset. In addition, we propose the parallelism of workload prediction model from the perspective of internal structure and data set to make AWAS apply to more computing nodes of the large-scale computing grids. Experimental results show that the combination of the two can achieve satisfactory acceleration efficiency. • In this paper, we propose an application and grid computing nodes workload aware scheduling algorithm (AWAS). • AWAS optimizes grid loads using greedy and heuristic methods. • This paper parallelizes the scheduling process of AWAS to improve its efficiency. • The experiment results show that the AWAS can achieve workload balancing in China National Grid. [ABSTRACT FROM AUTHOR]

Background: Computational fluid dynamics has been widely used to assist the design and evaluation of blood pumps. Discretization errors associated with computational grid may influence the credibility of numerical simulations. Non‐conformal grid interfaces commonly exist in rotary machines, including rotary blood pumps. Should grid size across the interface differ greatly, large errors may occur. Methods: This study explored the effects of non‐conformal grid interface on the prediction of the flow field and hemolysis in blood pumps using large eddy simulation (LES). Two benchmarks, a nozzle model and a centrifugal blood pump were chosen as test cases. Results: This study found that non‐conformal grid interfaces with considerable change of grid sizes led to discontinuities of flow variables and brought errors to metrics such as pressure head (7%) and hemolysis (up to 14%). Conclusions: The results on the full unstructured grid are more accurate with negligible changes of flow variables across the non‐conformal grid interface. A full unstructured grid should be employed for centrifugal blood pumps to minimize the influence of non‐conformal grid interfaces for LES simulations. [ABSTRACT FROM AUTHOR]

Existing mesh generators are focused mainly on obtaining non-orthogonal irregular grids designed to describe the curved boundaries of streamlined bodies. However, the thickening of the grid leads to an increase in the calculation time, and the non-conformity of the grid leads to unphysical effects. The software package (SP) developed by the authors for the simulation of gas-thermodynamic processes is oriented toward a much simpler description of the geometry, i. e., uses a different principle of increasing the smoothness of the solution in places with a complex surface structure. This principle consists in superimposing on the flow such sources of momentum and energy, which are equivalent in their effect on the flow to the interaction with the solid wall. SP contains a mask generator of an orthogonal regular grid. The initial data for building the mask is a 3D model created in any CAD application, which is saved in the STL format and placed in the project directory. Each cell contains information about the presence of a three-dimensional solid, the permeability of each face of the hexahedron, and the direction of the normal vector to the streamlined surface. In this regard, the generator creates three types of masks: volumetric, surface full and incomplete permeability, as well as a mask of guiding cosines. To obtain a volume (solid) mask from the center of each cell along the axes, a straight line is drawn and its intersection is checked with each triangle approximating the surface of the body under study. An odd number of intersections of triangles and a straight line indicates the presence of a volume mask in the cells. A surface impermeable mask is formed in three directions at the free cell section and the occupied volume mask. If it is necessary to introduce a semipermeable mask, its localization and measure are assigned by the user. The mask of the guiding cosines is assigned in the cell, which is adjacent to the surface impermeable mask. The values of the guiding cosines are assigned equal to the corresponding values of the nearby triangle approximating the surface of the 3D model. The generated masks are formed as separate files. A SolidWorks application has been developed that allows for volumetric visualization. In the decisive program, the information about the presence of the volume mask is used as follows: the volume mask is excluded from the solution area, self-similar problems are solved near the surface, and if there are guiding properties, an isentropic flow rotation is performed.

Computational grid is a pool of computational resources that is used by various organizations for storage purposes and execution of a large number of tasks. Load balancing and energy consumption are two core performance parameters in the computational grid. Since, performance of a computational grid is highly dependable to variations in load and energy consumption, therefore, it is important to pay attention to these aspects in grid. Therefore, we proposed an energy‐aware dynamic load balancing strategy for tasks scheduling in grid referred to as dynamic energy efficient load balancing strategy (DEEL) for computational grid. DEEL combined energy efficiency and load balancing paradigms in order to improve the utilization and reduce the energy consumption of resources. Simulations were performed by using GridSim. Simulation results were compared with published strategy IEGDC with respect to performance indices: finished gridlets, unfinished gridlets, resubmitted times, and response time. The simulation results were evaluated through performance metrics that is, (a) cost, (b) energy consumption, and (c) energy saved. As per simulation results, DEEL outperformed the published method IEGDC by reducing the execution time of finished gridlets up to 28%, minimizing the execution and resource cost up to 35%, and saving the energy consumption up to 38%. [ABSTRACT FROM AUTHOR]

In this paper, the investigation was performed to determine the effect of leading-edge angle and leading-edge sweep on the aerodynamic coefficients of the projectile geometry and analyze the effect of roll moment on the fins at various operating conditions. A group of four models were considered, standard TTCP with the blunt leading edge and with 45° leading-edge along with modified TTCP with the blunt leading edge along with 30° sweep and with 45° leading-edge along with 30° sweep. The flow field solutions were obtained and considered as a function of roll moment coefficients, which are then compared to other numerical models and experimental results. The standard wraparound TTCP models were subjected to varying velocities ranging from Mach 1.5 to 2.5. WAFs are considered a choice for spinning tube-launched projectiles because of their high packing factor and instant deployment. The computational grids have been built to accurately reflect the fin edge shape of the experimental model. The significant parameter of the WAF is the rolling moment, that was computed using CFD and compared with available experimental test data. [ABSTRACT FROM AUTHOR]

A material requirement planning (MRP) process generates a production plan which guarantees an exact quantity of the right materials available at the needed time. Providing an executable production plan at high speed has remained a goal for MRP since the process was first developed in the 1970s. However, due to the time consuming characteristic of the process with its intensive database interaction, real time processing remained unattainable. Moreover, this performance issue became worse, as the utilisation of production resources on the shop floor are expected to be maximised by the process due to a dynamic market environment. This paper presents a recent work by the authors on the concept of using a computational grid to achieve a breakthrough in its performance under conditions of finite capacity. The proposed system resolves capacity constraints by applying a simple heuristic called longest tail first rule, which is proved to minimise the total lead time, to each distributed cluster obviating the need for any rescheduling procedures. Implementation of this concept in a distributed database environment and its performance analysis are described. The experimental results suggest that the proposed finite capacitated MRP process has desirable characteristics in terms of processing time with a deep bill of material as in current supply chain practice. [ABSTRACT FROM AUTHOR]

Load balancing is a very important and complex problem in computational grids. In load balancing, jobs should be effectively distributed among resources in order to minimize the average completion time and maximize the utilization of all resources even those with low reliabilities and capacities. However, using the less reliable and slow resources implies worse completion time, whereas always selecting the powerful and reliable resources undermines the utilization of other resources. So, it is essential to develop an efficient load balancing method which makes a good tradeoff between these criteria in a way that satisfies the quality of service of jobs and fairly distributes jobs between resources based on their reliabilities and capacities. This paper proposes an efficient multicriteria load balancing method using technique for order preference by similarity to ideal solution which treats load balancing as a multi criteria decision making problem. Also, an effective weighting mechanism is proposed, which adaptively adjusts the weights of the considered criteria according to the system's current state and jobs' characteristics. This mechanism can make an efficient tradeoff between the considered criteria and accurately reflect the importance of each one. By simulation, the proposed method was evaluated and compared with other approaches from the literature. In the range of examined parameters' values, the simulation results show that proposed method minimizes the average completion time by 8.7–15.7%, increases the throughput ratio up to 15.8–19.4%, and maximizes the load balancing level by 7.68–20.1%. [ABSTRACT FROM AUTHOR]

Algorithms of the optimal arrangement of heat sources with volumetric heat release within regions of a complex geometric shape are considered. The distribution found has the minimum total power and provides the temperature in the given temperature corridor. Finite-dimensional approximations of the original problem are constructed in the form of a linear programming problem. A method is given for constructing a finite-difference scheme for solving the heat equation, as well as a brief description of the developed software modules for constructing grids and solving equations. Several computer experiments have been carried out using the developed programs. [ABSTRACT FROM AUTHOR]

Computational grid (CG) environment has a group of autonomous dissimilar distributed computing systems to provide service to user tasks. To attain the auspicious usefulness of CG resources, basically best scheduling algorithms are important. The CG service users are very cautious in time needed for task completion. To meet multiple requirements of the user, the job allocation problem in CG is designed as a multi-objective problem. Evolutionary algorithms have an efficient meta-heuristic technique for optimization problem solving. This work introduces a MapReduce model for non-dominated sorting genetic algorithm (NSGA-II) for independent job scheduling in a CG. This research work attempts to find the optimal schedules by considering makespan and flowtime minimization. A fuzzy membership function is used to analyze the efficiency of the schedule. Set of benchmark instances is used to test the algorithm. Experimental results show that MapReduce model-based NSGA-II generated finer solutions in less time than the MapReduce model-based weighted sum multi-objective genetic algorithm (WMOGA) which is also implemented in this paper. [ABSTRACT FROM AUTHOR]

In a heterogeneous distributed computing environment, developing a fault tolerance mechanism is a key research issue. Most of the existing fault tolerance approaches for distributed computing environment are post-active. These post-active approaches, predominantly involve the heartbeat strategy for fault detection and the checkpointing mechanism for fault recovery. In this proposed work, a proactive Health Aware Fault Tolerant (HAFT) scheduler using the Cox Proportional Hazard survival probability model is developed. The survival probability of the resource is estimated using resource failure data analytics and termed as health coefficient of the resource. For the job distribution classes jclass1, jclass2, and jclass3, the average improvement for makespan in HAFT algorithm over the compared algorithms are 44, 59.6, and 26.4%. In a heterogeneous environment, the job failure rate of the HAFT scheduler is ranging between 15 and 20% and it is stable for all the three jclasses. In a homogenous environment, the job failure rate of HAFT algorithm in comparison to IRP, REP and MJSP algorithm is considerably reduced by 58.6, 26.4, and 11.6%, respectively. For a failure probability higher than 0.4, the resource efficiency of HAFT algorithm on an average is 26% more than MJSP and 53% more than REP. [ABSTRACT FROM AUTHOR]

Provisioning fault-tolerant scheduling in computational grid is a challenging task. Most of the existing fault tolerant scheduling schemes are either geared toward proactive or reactive. Proactive schemes emphasize on the reasons responsible for generating faults, whereas reactive mechanisms come into effect after failure detection. Unlike most existing mechanisms, we present a novel, dynamic, adaptive, and hybrid fault-tolerant scheduling scheme based on proactive and reactive approaches. In the proactive approach, the resource filtration algorithm picks resources based on resource location, availability, and reliability. Unlike most existing schemes, which rely on remotely connected resources, the proposed algorithm prefers to employ locally available resources as they might have less failure tendency. To cope with the frequent turnover problem, the proposed scheme calculates resource availability time based on various newly identified parameters (e.g., mean time between availability) and picks highly available nodes for task execution. Resource reliability is an indispensable consideration in the proposed scheme and is calculated based on parameters such as jobs success or failure ratio and the types of failures encountered. We employ an optimal resource identification algorithm to determine and select optimal resources for job execution. The performance of the proposed scheme is validated through the GridSim toolkit. Compared with contemporary approaches, experimental results demonstrate the effectiveness and efficiency of the proposed scheme in terms of various performance metrics, such as wall clock time, throughput, waiting and turnaround time, number of checkpoints, and energy consumption.