Both the system reliability and the resilience evaluation of multi-state flow networks (MFNs) play a crucial role in designing and analyzing these networks. The system reliability at level d is the probability of succ...
详细信息
Both the system reliability and the resilience evaluation of multi-state flow networks (MFNs) play a crucial role in designing and analyzing these networks. The system reliability at level d is the probability of successfully transmitting at least d units of flow. In turn, system resilience allows us to analyze the ability of systems to withstand and bounce back from disruptive events. The paper presents a new simulation approach based on minimal cuts (MCs) and parallel computations to compute the system reliability for all possible non-integer levels. An extension with a time attribute is also considered to investigate the reliability degradation with time. Moreover, it also introduces a novel heuristic that for a given integer K and a state vector x, finds an MC for which the capacity under the system state x is the smallest among MCs containing some of K coordinates of x with the smallest capacities. It is also shown how this approach can be used to compute the network resilience at a given time and the system integrated resilience metric is introduced. Numerical experiments are conducted to demonstrate the efficiency and advantages of the presented algorithm.
Purpose - A variety of meshless methods have been developed in the last 20 years with an intention to solve practical engineering problems, but are limited to small academic problems due to associated high computation...
详细信息
Purpose - A variety of meshless methods have been developed in the last 20 years with an intention to solve practical engineering problems, but are limited to small academic problems due to associated high computational cost as compared to the standard finite element methods (FEM). The purpose of this paper is to develop an efficient and accurate algorithms based on meshless methods for the solution of problems involving both material and geometrical nonlinearities. Design/methodology/approach - A parallel two-dimensional linear elastic computer code is presented for a maximum entropy basis functions based meshless method. The two-dimensional algorithm is subsequently extended to three-dimensional adaptive nonlinear and three-dimensional parallel nonlinear adaptively coupled finite element, meshless method cases. The Prandtl-Reuss constitutive model is used to model elasto-plasticity and total Lagrangian formulations are used to model finite deformation. Furthermore, Zienkiewicz and Zhu and Chung and Belytschko error estimation procedure are used in the FE and meshless regions of the problem domain, respectively. The message passing interface library and open-source software packages, METIS and MUltifrontal Massively parallel Solver are used for the high performance computation. Findings - Numerical examples are given to demonstrate the correct implementation and performance of the parallel algorithms. The agreement between the numerical and analytical results in the case of linear elastic example is excellent. For the nonlinear problems load-displacement curve are compared with the reference FEM and found in a very good agreement. As compared to the FEM, no volumetric locking was observed in the case of meshless method. Furthermore, it is shown that increasing the number of processors up to a given number improve the performance of parallel algorithms in term of simulation time, speedup and efficiency. Originality/value - Problems involving both material and geomet
The article presents a method of computing the step response of an air floor heater. The method implements parallel algorithms on a graphics processing unit. In the analyzed concrete slab heating ducts are placed. Hot...
详细信息
The article presents a method of computing the step response of an air floor heater. The method implements parallel algorithms on a graphics processing unit. In the analyzed concrete slab heating ducts are placed. Hot air is transferred through them, thanks to which the heat penetrates into the slab. Heat transfer into the environment takes place on the top surface of the floor by natural convection and radiation. The bottom surface of the slab is thermally insulated. A two-dimensional heat equation was discretized with the use of the implicit finite difference method. In order to solve the obtained system of equations, the conjugate gradient method was used. Moreover, in order to examine the possibility of shortening the computations time, the algorithm of this method was implemented on a graphics processing unit. A computer program, using the CUDA parallel computing platform and linear algebra libraries CUBLAS and CUSPARSE, was developed.
Pedigree data structures have a number of applications in genetics, including the estimation of allelic or haplotype probabilities in humans and agricultural species, and the estimation of breeding values in agricultu...
详细信息
Pedigree data structures have a number of applications in genetics, including the estimation of allelic or haplotype probabilities in humans and agricultural species, and the estimation of breeding values in agricultural species. Sequential algorithms for general purpose CPU-based computers are commonly used, but are inadequate for some tasks on large data sets. We show that pedigree data can be directly represented on Field Programmable Gate Arrays (FPGA), allowing highly efficient massively parallel simulation of the flow of genes. Operating on the whole pedigree in parallel, the transmission of genes can occur for all individuals in a single clock cycle. By using FPGA, the algorithms to estimate inbreeding coefficients and allelic probabilities are shown to operate hundreds to thousands of times faster than the corresponding sequentially based algorithms. Where problems can be largely represented in an integer form, FPGA provide an efficient platform for computations on pedigree data.
The paper presents Comcute which is a novel multi-level implementation of the volunteer based computing paradigm. Comcute was designed to let users donate the computing power of their PCs in a simplified manner, requi...
详细信息
ISBN:
(纸本)9783642552243
The paper presents Comcute which is a novel multi-level implementation of the volunteer based computing paradigm. Comcute was designed to let users donate the computing power of their PCs in a simplified manner, requiring only pointing their web browser at a specific web address and clicking a mouse. The server side appoints several servers to be in charge of execution of particular tasks. Thanks to that the system can survive failures of individual computers and allow definition of redundancy of desired order. On the client side, computations are executed within web browsers using technologies such as Java, JavaScript, Adobe Flash etc. without the need for installation of additional software. This paper presents results of scalability experiments carried on the Comcute system.
The article is devoted to a new approach to the analysis and modeling of short geoacoustic signals. A parallel implementation of the applied methods is described.
ISBN:
(纸本)9781538618103
The article is devoted to a new approach to the analysis and modeling of short geoacoustic signals. A parallel implementation of the applied methods is described.
The paper considers the monitoring of parallel computations for detection of abnormal events. It is assumed that computations are organized according to an event model, and monitoring is based on specific test sequences.
The paper considers the monitoring of parallel computations for detection of abnormal events. It is assumed that computations are organized according to an event model, and monitoring is based on specific test sequences.
In this paper, we investigate the modeling and analysis of time cost behavior of parallel computations. It is assumed parallel computations under investigation reside in a computer system in which there is a limited n...
详细信息
In this paper, we investigate the modeling and analysis of time cost behavior of parallel computations. It is assumed parallel computations under investigation reside in a computer system in which there is a limited number of processors, all the processors have the same speed, and they communicate with each other through a shared memory. It has been found the time costs of parallel computations depend on the input, the algorithm, the data structure, the processor speed, the number of processors, the processing power allocation, the communication, the execution overhead, and the execution environment. In this paper, we define time costs of parallel computations as a function of the first seven factors as listed above. The computation structure model is modified to describe the impact of these seven factors on time cost. Techniques based on the modified computation structure model are developed to analyze time cost. A software tool, TCAS (time cost analysis system) that uses both the analytic and the simulation approaches, is designed and implemented to aid users in determining the time cost behavior of their parallel computations.
In this paper, we introduce an analytical technique based on queueing networks and Petri nets for making a performance analysis of dataflow computations when executed on the Manchester machine. This technique is also ...
详细信息
In this paper, we introduce an analytical technique based on queueing networks and Petri nets for making a performance analysis of dataflow computations when executed on the Manchester machine. This technique is also applicable for the analysis of parallel computations on multiprocessors. We characterize the parallelism in dataflow computations through a four-parameter characterization, namely, the minimum parallelism, the maximum parallelism, the average parallelism and the variance in parallelism. We observe through detailed investigation of our analytical models that the average parallelism is a good characterization of the dataflow computations only as long as the variance in parallelism is small. However, significant difference in performance measures will result when the variance in parallelism is comparable to or higher than the average parallelism.
A new approach is proposed for the solution of large-scale constrained optimal control problems. The method is based on aggregation-disaggregation ideas and is within the class of feasible decomposition methods (Singh...
详细信息
A new approach is proposed for the solution of large-scale constrained optimal control problems. The method is based on aggregation-disaggregation ideas and is within the class of feasible decomposition methods (Singh and Tilti, Systems: Decomposition, Optimization and Control. Pergamon Press, Oxford 1978). It is shown that the problem of updating the disaggregation in each iteration decomposes into independent subproblems of lower dimension. Numerical results are presented.
暂无评论