Search

Abstract: String match algorithm is widely used in the area of data mining. In this paper, we present an approach for elevating the performance of this algorithm via GPU (Graphic Processing Unit). With the rapid development of Graphics Processing Unit to many-core multiprocessors, it shows great potential in many applications and high performance computing. Especially, the heterogeneous architecture CPU+GPU shows enthusiastic capacity to accelerate parallel applications. Till now, some research has been done for parallel implementation of string match algorithm on GPU. But there are some constraints for acceleration of this algorithm: firstly, if-branch exists in the algorithm which can cripple the performance of the parallel implementation; secondly, improper memory access may bring heavy latency generated by bank-conflict. This paper presents the optimization of global memory access, shared memory access and the elimination of if-branch for elevating the performance of string match algorithm BMH. Meanwhile, we explore the interesting characteristics of the parallel BMH string match algorithm implemented on GPU using CUDA. We found that the performance elevation is affected by the characteristic of pattern, which also proves the potential of GPU. [Copyright &y& Elsevier]

Abstract: Distributed Generation (DG), and especially microturbine generation (MTG) system, plays a significant role in Smart Grids. One of the most important variables of a MTG system is the governer speed. This paper defines a problem on transient speed response of MTs for a step load. The aim is to optimize the speed governer parameters in order to minimize the transient response of MTG. Differential Evolutionary Algorithm (DEA) is employed to solve the problem. The stability issue of the MTG system is also discussed in the paper. The simulation results show the effectiveness of a fine-tuned speed governer by using the proposed method. [Copyright &y& Elsevier]

Abstract: Distributed generation (DG), and especially microturbine generation (MTG) system, plays a significant role in Smart Grids. One of the most important variables of a MTG system is the fuel consumption. This paper defines a problem on fuel consumption of MTs for a sample load change that can be used for a 24-hour load change pattern. The aim is to optimize the speed governer parameters in order to minimize the fuel consumption of MTG. Differential Evolutionary Algorithm (DEA) is employed to solve the problem. The stability issue of the MTG system is also discussed in the paper. The simulation results show the effectiveness of a fine-tuned speed governer by using the proposed method. [Copyright &y& Elsevier]

Abstract: Chaos immune optimization algorithm on distribution service restoration after faults is presented to improve the probability for optimal solution in this paper, which is integrated the characteristic of chaotic optimization with artificial immunity algorithm. In the proposed algorithm, excellent global search ability of chaotic optimization is regarded as “thick search” to initialize the antibody of immune algorithm, and local search of artificial immune algorithm is applied to replace “thin search” in the chaotic optimization, which assures the population diversity and avoids getting to stuck in local minima to a certain degree. A living example for a certain district distribution in Chongqing is analyzed by the method presented in this paper. The result shows that chaos immune optimization algorithm in the paper might improve convergence speed and precision of restoration and avoid premature convergence. [Copyright &y& Elsevier]

Abstract: Grover quantum search algorithm access the unsorted database O(N) times, however, the probability of acquiring solutions usually falls with the increase of the number of solutions, the reason of which is analyzed. To improve the performance of converging and optimizing for the intelligent optimization, some quantum evolutionary algorithms are proposed by domestic and foreign scholars. In this paper, a lot of improved Grover quantum search algorithms are introduced in detail. [Copyright &y& Elsevier]

Abstract: Graph drawing problems can be applied to many reality places, which also deduce to some important graph drawing problems. Such as aesthetics criteria whose optimization can lead to acceptable drawings. This paper gives an algorithm for optimizing these criteria. We propose a new force-directed model to solve the graph drawing problems in 2-D frames and modify this hybrid force model to promote to normal drawing frame shape, especially regular triangle and circle drawing frames. For the regular triangle drawing frame, it can be applied to tree drawing problems and for the circle drawing frame shape we use it to suit the normal graph drawing problems. [Copyright &y& Elsevier]

Abstract: As a latest video compression coding standard, the H.264/AVC has significant improvement in coding efficiency compared with the previous H.263, MPEG-4 coding standards, but the large amount of motion estimation greatly affect the coding complexity. In order to reduce the time of motion estimation, the UMHexagonS and EPZS algorithm in JM test model of H.264 coding standard are close analyzed in this paper, meanwhile combining with the advantages of the two algorithms, improving the new SAD of the motion estimation and adaptive all-zero blocks processing. Experiment results show that the proposed algorithm greatly reduced the motion estimation time and complexity while maintaining coding efficiency. [Copyright &y& Elsevier]

Abstract: In this paper, a kind of nonlinear optimization problems with nonlinear equality and inequality constraints are discussed, and a new algorithm with arbitrary initial point is presented by combining the norm-relaxed method of feasible direction for inequality constrained optimization with the idea of strongly sub-feasible direction method and the two concepts of quasi-KKT point and quasi-multiplier method. Firstly, the original problem is transformed into an associated simpler problem with only inequality constraints and a parameter. The later problem is shown to be approximately equivalent to the original problem if the parameter is large enough (but finite). At each iteration of the proposed algorithm, a direction is obtained by solving one direction finding subproblem which always possesses a solution. Some good properties of the new algorithm are that the initial iteration point is arbitrary and the number of the constraint functions satisfying the inequality constraints is nondecreasing. The algorithm is proved to be globally and strongly convergent under mild conditions. Finally, the numerical experiments are implemented on Matlab7.0. [Copyright &y& Elsevier]

Abstract: Clustering is an example of a class of optimization problems. In the classical clustering, an item must belong to any one cluster. But fuzzy clustering describes more accurately the ambiguous type of structure in data. The fuzzy ISODATA clustering exhibits the rapid convergence in finding the best classification program when the classification number is given. In this paper, we propose the algorithm to solve the choosing lands problem and show the result of the experiment. The result is satisfied to realtors in choosing lands. [Copyright &y& Elsevier]

Abstract: The parallelization of geo-computation is one of the kernels in High Performance Geographic Computing (HPGC). To gain the benefit provided by multi-core computer, lots of effort has been done on parallelizing classical serial algorithms, one of which is the plane sweep algorithm (PSA). A framework of parallelization when intersecting two sets of segments has been suggested. However, when focusing on the Minimum Bounding Rectangles (MBRs) in the filtration process in GIS, different optimization needs to be considered. In this paper, a parallel version of MBR based PSA is designed and implemented using OpenMP. The experiment results show that by carefully choosing the number of threads and semi-sets, the proposed algorithm can significantly outperform the serial version on real-life data sets with a high speed-up. [Copyright &y& Elsevier]

Abstract: An improved spectral clustering approach based on differential evolution algorithm (DESC) is proposed in this paper. In our algorithm, we replace k-means with differential evolution (DE) as the final step in spectral clustering, thus it overcomes the deficiencies in sensitivity to initialization and local optima. Experimental results over artificial dataset and UCI dataset demonstrate DESC''s superiority in difficult clustering, steady performance and better accuracy. [Copyright &y& Elsevier]

Abstract: A new quantum-behaved particle swarm optimization algorithm with inverse proportional inertia weight is presented and proved in this paper. Also a robust design method of optimization is used by optimizing the robustness of both the system objective function and constraint functions in solving the problem of breach of condition to the constraint functions. Comparing the solution of the traditional optimization and the solution of the robust optimal design, the robust design parameters display a significant stability in performance when the value of the parameters changed and all the optimizations are solved by this new efficient algorithm. [Copyright &y& Elsevier]

Abstract: Optimized configuration of energy industry is an issue for resource combination and optimization, which includes continuous variable and discrete variable and belongs to the optimal power flow research. In order to improve the solution quality and the counting efficiency, this paper gives the solution using the mixed Greedy Algorithm and Genetic Algorithm: Use the superiority of Greedy Algorithm to obtain the original resource distribution solution space in the structure. This algorithm can minimize the spatial scale. And then utilizes the Genetic Algorithm to select the original solution space based on the overall situation and improve its application efficiency. The test case matches the anticipation. [Copyright &y& Elsevier]