Distributed evolutionary multi-objective mesh-partitioning algorithm for parallel finite element computations

Majority of the mesh-partitioning algorithms attempt to optimise the interprocessor communications, while balancing the computational load among the processors. However, it is desirable to simultaneously optimise the submesh aspect ratios in order to significantly improve the convergence characteristics of the domain decomposition based Preconditioned-conjugate-gradient algorithms, being used extensively in the state-of-the-art parallel finite element codes. Keeping this in view, a new distributed multi-objective mesh-partitioning algorithm using evolutionary computing techniques is proposed in this paper. Effectiveness of the proposed distributed mesh-partitioning algorithm is demonstrated by solving several unstructured meshes of practical-engineering problems and also benchmark problems.     

Solving the mesh-partitioning problem with an ant-colony algorithm

Many real-world engineering problems can be expressed in terms of partial differential equations and solved by using the finite-element method, which is usually parallelised, i.e. the mesh is divided among several processors. To achieve high parallel efficiency it is important that the mesh is partitioned in such a way that workloads are well balanced and interprocessor communication is minimised. In this paper we present an enhancement of a technique that uses a nature-inspired metaheuristic approach to achieve higher-quality partitions. The so-called multilevel ant-colony algorithm, which is a relatively new metaheuristic search technique for solving optimisation problems, was applied and studied, and the possible parallelisation of this algorithm is discussed. The multilevel ant-colony algorithm performed very well and is superior to classical k-METIS and Chaco algorithms; it is even comparable with the combined evolutionary/multilevel scheme used in the JOSTLE evolutionary algorithm and returned solutions that are better than the currently available solutions in the Graph Partitioning Archive.     

Parallel genetic algorithms: a survey and problem state of the art

In relation with development of computer capabilities and the appearance of multicore processors, parallel computing made it possible to reduce the time for solution of optimization problems. At present of interest are methods of parallel computing for genetic algorithms using the evolutionary model of development in which the main component is the population of species (set of alternative solutions to the problem). In this case, the algorithm efficiency increases due to parallel development of several populations. The survey of basic parallelization strategies and the most interesting models of their implementation are presented. Theoretical ideas on improvement of existing parallelization mechanisms for genetic algorithms are described. A modified model of parallel genetic algorithm is developed. Since genetic algorithms are used for solution of optimization problems, the proposed model was studied for the problem of optimization of a multicriteria function. The algorithm capabilities of getting out of local optima and the influence of algorithm parameters on the deep extremum search dynamics were studied. The conclusion on efficiency of application of dynamic connections of processes, rather than static connections, is made. New mechanisms for implementation and analysis of efficiency of dynamic connections for distributed computing in genetic algorithms are necessary.     

基于混合人工蜂群算法的并行测试任务优化研究

并行测试技术可以同时进行多个任务的测试,提高资源利用率,节约测试成本;并行测试调度问题是一种复杂的组合优化问题,是并行测试技术的核心要素;并行测试系统作为并行测试技术的载体,自身的性能和求解效率尤其重要;对并行测试完成时间极限定理进行了研究,建立了并行测试任务调度的数学模型,分析了传统元启发式算法求解并行测试问题的不足,提出了基于动态规划的递归搜索技术和人工蜂群算法相结合的混合人工蜂群算法,并采用整数规划精确算法和遗传算法对混合人工蜂群算法进行验证;得出结论采用混合人工蜂群算法进行并行测试任务的调度节约了接近50%的时间,降低了约20%的硬件资源占用,提高了测试效率,可以满足工程实际的应用。     

A diversity control mechanism in many objective optimizations

Multi-objective evolutionary optimization algorithms are among the best optimizers for solving problems in control systems, engineering and industrial planning. The performance of these algorithms degrades severely due to the loss of selection pressure exerted by the Pareto dominance relation which will cause the algorithm to act randomly. Various recent methods tried to provide more selection pressure but this would cause the population to converge to a specific region which is not desirable. Diversity reduction in high dimensional problems which decreases the capabilities of these approaches is a decisive factor in the overall performance of these algorithms. The novelty of this paper is to propose a new diversity measure and a diversity control mechanism which can be used in combination to remedy the mentioned problem. This measure is based on shortest Hamiltonian path for capturing an order of the population in any dimension. In order to control the diversity of population, we designed an adaptive framework which adjusts the selection operator according to diversity variation in the population using different diversity measures as well as our proposed one. This study incorporates the proposed framework in MOEA/D, an efficient widely used evolutionary algorithm. The obtained results validate the motivation on the basis of diversity and performance measures in comparison with the state-of-the-art algorithms and demonstrate the applicability of our algorithm/method in handling many-objective problems. Moreover, an extensive comparison with several diversity measure algorithms reveals the competitiveness of our proposed measure.     

Evolutionary Algorithms for Minimax Problems in Robust Design

Many robust design problems can be described by minimax optimization problems. Classical techniques for solving these problems have typically been limited to a discrete form of the problem. More recently, evolutionary algorithms, particularly coevolutionary optimization techniques, have been applied to minimax problems. A new method of solving minimax optimization problems using evolutionary algorithms is proposed. The performance of this algorithm is shown to compare favorably with the existing methods on test problems. The performance of the algorithm is demonstrated on a robust pole placement problem and a ship engineering plant design problem.     

基于不确定度采样准则的费时问题优化算法

在实际工程和控制领域中,许多优化问题的性能评价是费时的,由于进化算法在获得最优解之前需要大量的目标函数评价,无法直接应用其求解这类费时问题.引入代理模型以辅助进化算法是求解计算费时优化问题的有效方法,如何采样新个体对其进行真实的目标函数评价是影响代理模型辅助的进化算法寻优性能的重要因素.鉴于此,利用径向基函数神经网络作...     

Minimizing Communication Penalty of Triangular Solvers by Runtime Mesh Configuration and Workload Redistribution

In this article, we study the effects of network topology and load balancing on the performance of a new parallel algorithm for solving triangular systems of linear equations on distributed-memory message-passing multiprocessors. The proposed algorithm employs novel runtime data mapping and workload redistribution methods on a communication network which is configured as a toroidal mesh. A fully parameterized theoretical model is used to predict communication behaviors of the proposed algorithm relevant to load balancing, and the analytical performance results correctly determine the optimal dimensions of the toroidal mesh, which vary with the problem size, the number of available processors, and the hardware parameters of the machine. Further enhancement to the proposed algorithm is then achieved through redistributing the arithmetic workload at runtime. Our FORTRAN implementation of the proposed algorithm as well as its enhanced version has been tested on an Intel iPSC/2 hypercube, and the same code is also suitable for executing the algorithm on the iPSC/860 hypercube and the Intel Paragon mesh multiprocessor. The actual timing results support our theoretical findings, and they both confirm the very significant impact a network topology chosen at runtime can have on the computational load distribution, the communication behaviors and the overall performance of parallel algorithms.     

Systolic neighborhood search on graphics processing units

In this paper, we propose a parallel processing model based on systolic computing merged with concepts of evolutionary algorithms. The proposed model works over a Graphics Processing Unit using the structure of threads as cells that form a systolic mesh. Data passes through those cells, each one performing a simple computing operation. The systolic algorithm is implemented using NVIDIA’s compute unified device architecture. To investigate the behavior and performance of the proposed model we test it over a NP-complete problem. The study of systolic algorithms on GPU and the different versions of the proposal show that our canonical model is a competitive solver with efficacy and presents a good scalability behavior across different instance sizes.     

Scheduling algorithm based on evolutionary computing in identical parallel machine production line

Evolutionary programming is a kind of evolutionary computing method based on stochastic search suitable for solving system optimization. In this paper, evolutionary programming method is applied to the identical parallel machine production line scheduling problem of minimizing the number of tardy jobs, which is a very important optimization problem in the field of research on CIMS and industrial engineering, and researches on problem formulation, expression of feasible solution, methods for the generation of the initial population, the mutation and improvement on the local search ability of evolutionary programming. Computational results of different scales of problems show that the evolutionary programming algorithm proposed in this paper is efficient, and that it is fit for solving large-scale identical parallel machine production line scheduling problems, and that the quality of its solution has advantage over so far the best heuristic procedure.     

非定常Monte Carlo输运问题的并行算法

文中给出了非定常MonteCarlo(下文简写为MC)输运问题的并行算法 ,对并行程序的加载运行模式进行了讨论和优化设计 .针对MC并行计算设计了一种理想情况下无通信的并行随机数发生器算法 .动态MC输运问题有大量的I/O操作 ,特别是读取剩余粒子数据文件需要大量的I/O时间 ,文中针对I/O问题 ,提出了三种并行I/O算法 .最后给出了并行算法的性能测试结果 ,对比串行计算时间 ,使用 6 4台处理机时的并行计算时间缩短了 30倍     

基于自适应机制的多宇宙并行量子衍生进化算法

进化参量的选取对量子衍生进化算法(QEA)的优化性能有极大的影响,传统QEA在选择进化参量时并未考虑种群中个体间的差异,种群中所有个体采用相同的进化参量完成更新,导致算法在解决组合优化问题中存在收敛速度慢、容易陷入局部最优解等问题。针对这一问题,采用自适应机制调整QEA的旋转角步长和量子变异概率,算法中任意一代的任一个体的进化参量均由该个体自身适应度确定,从而保证尽可能多的进化个体能够朝着最优解方向不断靠近。此外,由于自适应量子进化算法需要评估个体的适应度,导致运算时间较长,针对这一问题则采用多宇宙机制将算法分布于多个宇宙中并行实现,从而提高算法的执行效率。通过搜索多峰函数最优解和求解背包问题测试算法性能,结果表明,与传统QEA相比,所提出算法在收敛速度、搜索全局最优解及执行速度方面具有较好的表现。     

Human behavior-based optimization: a novel metaheuristic approach to solve complex optimization problems

Optimization techniques, specially evolutionary algorithms, have been widely used for solving various scientific and engineering optimization problems because of their flexibility and simplicity. In this paper, a novel metaheuristic optimization method, namely human behavior-based optimization (HBBO), is presented. Despite many of the optimization algorithms that use nature as the principal source of inspiration, HBBO uses the human behavior as the main source of inspiration. In this paper, first some human behaviors that are needed to understand the algorithm are discussed and after that it is shown that how it can be used for solving the practical optimization problems. HBBO is capable of solving many types of optimization problems such as high-dimensional multimodal functions, which have multiple local minima, and unimodal functions. In order to demonstrate the performance of HBBO, the proposed algorithm has been tested on a set of well-known benchmark functions and compared with other optimization algorithms. The results have been shown that this algorithm outperforms other optimization algorithms in terms of algorithm reliability, result accuracy and convergence speed.

     

Variable population size and evolution acceleration: a case study with a parallel evolutionary algorithm

With current developments of parallel and distributed computing, evolutionary algorithms have benefited considerably from parallelization techniques. Besides improved computation efficiency, parallelization may bring about innovation to many aspects of evolutionary algorithms. In this article, we focus on the effect of variable population size on accelerating evolution in the context of a parallel evolutionary algorithm. In nature it is observed that dramatic variations of population size have considerable impact on evolution. Interestingly, the property of variable population size here arises implicitly and naturally from the algorithm rather than through intentional design. To investigate the effect of variable population size in such a parallel algorithm, evolution dynamics, including fitness progression and population diversity variation, are analyzed. Further, this parallel algorithm is compared to a conventional fixed-population-size genetic algorithm. We observe that the dramatic changes in population size allow evolution to accelerate.     

基于交流的求解数值优化问题的混合演化算法

演化算法中有很多不同的演化算子,每一种算子对于不同的优化问题都有自己的优点和缺点。提出了一种基于交流模型的多算子混合演化算法。在该算法中,有两个种群,使用两种算子:多父体杂交算子和Cauchy变异算子。种群间的信息交换通过个体交流实现。对23个标准测试函数的数值仿真表明,该算法具有良好的全局收敛性和鲁棒性。     

Multiobjective evolutionary algorithm based on multimethod with dynamic resources allocation

In the last two decades, multiobjective optimization has become main stream and various multiobjective evolutionary algorithms (MOEAs) have been suggested in the field of evolutionary computing (EC) for solving hard combinatorial and continuous multiobjective optimization problems. Most MOEAs employ single evolutionary operators such as crossover, mutation and selection for population evolution. In this paper, we suggest a multiobjective evolutionary algorithm based on multimethods (MMTD) with dynamic resource allocation for coping with continuous multi-objective optimization problems (MOPs). The suggested algorithm employs two well known population based stochastic algorithms namely MOEA/D and NSGA-II as constituent algorithms for population evolution with a dynamic resource allocation scheme. We have examined the performance of the proposed MMTD on two different MOPs test suites: the widely used ZDT problems and the recently formulated test instances for the special session on MOEAs competition of the 2009 IEEE congress on evolutionary computation (CEC’09). Experimental results obtained by the suggested MMTD are more promising than those of some state-of-the-art MOEAs in terms of the inverted generational distance (IGD)-metric on most test problems.     

旅行商问题的闭环DNA算法

旅行商问题TSP是NP完全问题,在工程实践中有着广泛的应用,利用常规算法很难在多项式时间内解决。DNA计算是一种新兴的计算模式,与生俱来的强大并行计算能力使得它在解决众多NP问题上表现出了巨大的优势。尝试利用DNA计算中改进的闭环模型解决TSP问题。首先介绍了闭环DNA 计算模型及其改进;随后提出了一种基于改进的闭环模型求解TSP问题的算法,并对算法的实验过程进行了详细的描述;最后运用该算法解决了一个小规模的TSP问题算例,结果表明,该算法能在较低的时间复杂度内有效地解决TSP问题。     

Performance and performance modeling of a parallel algorithm for solving the neutron transport equation

A parallel algorithm is derived for solving the discrete-ordinates approximation of the neutron transport equation, based on the naturally occurring decoupling between the mesh sweeps in the various discrete directions during each iteration. In addition, the parallel Source Iteration (SI) algorithm, characterized by its coarse granularity and static scheduling, is implemented for the Nodal Integral Method (NIM) into the Parallel Nodal Transport (P-NT) code on Intel's iPSC/2 hypercube. Measured parallel performance for solutions of two test problems is used as evidence of the parallel algorithm's potential for high speedup and efficiency. The measured performance data are also used to develop and validate a parallel performance model for the total, serial, parallel, and global-summation time components per iteration as a function of the spatial mesh size, the problem size (number of mesh cells and angular quadrature order), and the number of utilized processors. The potential for high performance (large speedup at high efficiency) for large problems is explored using the performance model, and it is concluded that present applications in three-dimensional Cartesian geometry will benefit by concurrent execution on parallel computers with up to a few hundred processors.Research sponsored by the U.S. Department of Energy, managed by Martin Marietta Energy Systems, Inc., under contract No. DE-AC05-84OR21400.     

A hardware accelerator for Particle Swarm Optimization

The Particle Swarm Optimization or PSO is a heuristic based on a population of individuals, in which the candidates for a solution of the problem at hand evolve through a simulation process of a social adaptation simplified model. Combining robustness, efficiency and simplicity, PSO has gained great popularity as many successful applications are reported. The algorithm has proven to have several advantages over other algorithms that based on swarm intelligence principles. The use of PSO solving problems that involve computationally demanding functions often results in low performance. In order to accelerate the process, one can proceed with the parallelization of the algorithm and/or map it directly onto hardware. This paper presents a novel massively parallel coprocessor for PSO implemented using reconfigurable hardware. The implementation results show that the proposed architecture is up to 135× and not less than 20× faster in terms of optimization time when compared to the direct software execution of the algorithm. Both the accelerator and the processor used to run the software version are mapped into FPGA reconfigurable hardware.     

Euclidean distance transform for binary images on reconfigurable mesh-connected computers.

The distance calculation in an image is a basic operation in computer vision, pattern recognition, and robotics. Several parallel algorithms have been proposed for calculating the Euclidean distance transform (EDT). Recently, Chen and Chuang proposed a parallel algorithm for computing the EDT on mesh-connected SIMD computers (1995). For an nxn image, their algorithm runs in O(n) time on a two-dimensional (2-D) nxn mesh-connected processor array. In this paper, we propose a more efficient parallel algorithm for computing the EDT on a reconfigurable mesh model. For the same problem, our algorithm runs in O(log(2)n) time on a 2-D nxn reconfigurable mesh. Since a reconfigurable mesh uses the same amount of VLSI area as a plain mesh of the same size does when implemented in VLSI, our algorithm improves the result in [3] significantly.