Reconfigurable systems have been widely used in practical engineering, especially for the reconfigurable computing systems and reconfigurable manufacturing systems. The reliability of reconfigurable systems can be imp...
详细信息
Reconfigurable systems have been widely used in practical engineering, especially for the reconfigurable computing systems and reconfigurable manufacturing systems. The reliability of reconfigurable systems can be improved by components replacement or components rearrangement without changing their reliability. Combining the advantages of the rearrangement method and replacement method, an integrated method is proposed to improve the reconfigurable system reliability cost-effectively in this paper. Then, a 0-1 integer programming model of multi-objective optimization is established to obtain the reconfiguration with maximum system reliability and minimum reconfiguration cost based on the integrated method. The coarse-grained parallel genetic algorithm (CPGA) is introduced to solve the multi-objective model, while the multiple objectives problem can be converted into a single objective problem through the novel fitness function. Finally, three examples based on the production monitoring system are implemented to illustrate the effectiveness of the CPGA comparing with the replacement based geneticalgorithm. The changes of optimal reconfigurations with different parameters of the fitness function and different pre-determined system reliability are also discussed based on the examples.
The study presents a multi-objective scheduling model on nonidentical parallel machines (MOSP),and proposes a new geneticalgorithm based on a vector group encoding technique and immune *** MOSP is different from othe...
详细信息
The study presents a multi-objective scheduling model on nonidentical parallel machines (MOSP),and proposes a new geneticalgorithm based on a vector group encoding technique and immune *** MOSP is different from other scheduling problems on parallel machines for the following characteristic:Firstly,parallel machines are non-identical;Secondly,the sort of jobs processed on every machine can be restricted;Finally,take minimizing the total earliness penalty,and minimizing the total tardiness penalty,and minimizing the total completion time into account as a multi-objective *** the algorithm,its encoding method is simple and can effectively reflect the virtual scheduling *** initial method of population and genetic operator,such as selection,crossover,mutation,are also ***,an immune operator is adopted in order to guarantee variety of colony and improve quality of colony every ***,under the mode of master-slave control networks,parallel genetic algorithm is applied in order to adapt to lager scale and real-time scheduling *** experiments show that it is efficient,and is better than the common geneticalgorithm,and has the better parallel efficiency.
Gnomic information continues to flood, and this trend comes in the wake of the life sciences' rapid development. The eventuality has been an increase in the demand for more scalable and faster searching techniques...
详细信息
Gnomic information continues to flood, and this trend comes in the wake of the life sciences' rapid development. The eventuality has been an increase in the demand for more scalable and faster searching techniques, with the demand also proving urgent. Whereas a faster algorithm could be used to search biomedical data, the process of making gene prediction remains challenging. Particularly, the searching of biomedical data has been affirmed to be a simple gradient base approach. Therefore, indexing has been investigated with the aim of achieving a fast finite conventional rate. With biomedical expressed datasheet at hand, data-based large sequence identification has been achieved via the prefix pattern gene search algorithm. Imperative to note is that real-value expression matrices can replace microarray experimental gene expression data. To ensure that the genomic dataset's querying exhibits reductions in the overall retrieval time and that the time used for pattern array building is sped up, parallel partitioned methods have gained application. Notably, the central merit accruing from the latter method is that the majority of unrelated sequences are skipped. Also, these methods ensure that the real search problems are only decomposed to establish original database fractions. To ensure that the establishment of the gene's hidden information and similar characteristics is enhanced, large genetic data patterns are required.
Meta-heuristic search algorithms such as geneticalgorithms have been applied successfully to generate unit tests, but typically take long to produce reasonable results, achieve sub-optimal code coverage, and have lar...
详细信息
ISBN:
(纸本)9781728117362
Meta-heuristic search algorithms such as geneticalgorithms have been applied successfully to generate unit tests, but typically take long to produce reasonable results, achieve sub-optimal code coverage, and have large variance due to their stochastic nature. parallel genetic algorithms have been shown to be an effective improvement over sequential algorithms in many domains, but have seen little exploration in the context of unit test generation to date. In this paper, we describe a parallelised version of the many-objective sorting algorithm (MOSA) for test generation. Through the use of island models, where individuals can migrate between independently evolving populations, this algorithm not only reduces the necessary search time, but produces overall better results. Experiments with an implementation of parallel MOSA on the EVOSUITE test generation tool using a large corpus of complex open source Java classes confirm that the parallelised MOSA algorithm achieves on average 84% code coverage, compared to 79% achieved by a standard sequential version.
In this paper, the MPI master-slave parallel genetic algorithm is implemented by analyzing the basic geneticalgorithm and parallel MPI program, and building a Linux cluster. This algorithm is used for the test of max...
详细信息
In this paper, the MPI master-slave parallel genetic algorithm is implemented by analyzing the basic geneticalgorithm and parallel MPI program, and building a Linux cluster. This algorithm is used for the test of maximum value problems (Rosen brocks function) .And we acquire the factors influencing the master-slave parallel genetic algorithm by deriving from the analysis of test data. The experimental data show that the balanced hardware configuration and software design optimization can improve the performance of system in the complexity of the computing environment using the master-slave parallel genetic algorithms.
Cooperative dual-crane lifting is an important but challenging process involved in heavy and critical lifting tasks. This paper considers the path planning for the cooperative dual-crane lifting. It aims to automatica...
详细信息
Cooperative dual-crane lifting is an important but challenging process involved in heavy and critical lifting tasks. This paper considers the path planning for the cooperative dual-crane lifting. It aims to automatically generate optimal dual-crane lifting paths under multiple constraints, i.e., collision avoidance, coordination between the two cranes, and balance of the lifting target. Previous works often used oversimplified models for the dual-crane lifting system, the lifting environment, and the motion of the lifting target. They were thus limited to simple lifting cases and might even lead to unsafe paths in some cases. We develop a novel path planner for dual-crane lifting that can quickly produce optimized paths in complex 3-D environments. The planner has fully considered the kinematic structure of the lifting system. Therefore, it is able to robustly handle the nonlinear movement of the suspended target during lifting. The effectiveness and efficiency of the planner are enabled by three novel aspects: 1) a comprehensive and computationally efficient mathematical modeling of the lifting system;2) a new multiobjective parallel genetic algorithm designed to solve the path planning problem;and 3) a new efficient approach to perform continuous collision detection for the dual-crane lifting target. The planner has been tested in complex industrial environments. The results show that the planner can generate dual-crane lifting paths that are easy for conductions and optimized in terms of costs for complex environments. Comparisons with two previous methods demonstrate the advantages of the planner, including safer paths, higher success rates, and the ability to handle general lifting cases.
This paper employs a parallelized geneticalgorithm in generating long-term bounded halo orbit and optimizing transfer trajectory from earth to it in the full ephemeris model. While the conventional gradient methods a...
详细信息
This paper employs a parallelized geneticalgorithm in generating long-term bounded halo orbit and optimizing transfer trajectory from earth to it in the full ephemeris model. While the conventional gradient methods are lacking in precision as well as time-consuming, the parallel genetic algorithm (PGA) offers an access to large-scale computing based on the advanced hardware capability. Abounded halo orbit without any stationkeeping maneuver in five periods is obtained inside a defined pipe region in the ephemeris model. Transfer trajectory from earth to the obtained halo orbit is also investigated in this paper. By optimizing insertion impulses in the backward propagation and midcourse in the forward propagation, a transfer trajectory from earth to halo with least fuel consumption is generated. Furthermore, launch window is investigated based on the periodic variation about inclination of the injection point on the parking orbit. Amapping method from spatial space to i- subspace is introduced for solving the time delay and position deviation problem. The numerical method employed in this paper is of high accuracy based on large-scale computing capability as well as efficient without any analytical initial guess, which makes it extensive in designing these unstable libration point orbits.
In this study, we present three methods of sharing knowledge between cooperative compact geneticalgorithms. The methods exploit the effect of the worse solutions of the two-cooperative compact geneticalgorithms to t...
详细信息
ISBN:
(纸本)9781538663509
In this study, we present three methods of sharing knowledge between cooperative compact geneticalgorithms. The methods exploit the effect of the worse solutions of the two-cooperative compact geneticalgorithms to the search space which can prevent premature convergence. The benefit also encourages exploring other areas in solution space which enhance the opportunity to discover the better solutions. The proposed algorithm has a simple structure requires much less execution time than the non-sharing compact geneticalgorithm.
The classification system is very important for making decision and it has been attracted much attention of many researchers. Usually, the traditional classifiers are either domain specific or produce unsatisfactory r...
详细信息
The classification system is very important for making decision and it has been attracted much attention of many researchers. Usually, the traditional classifiers are either domain specific or produce unsatisfactory results over classification problems with larger size and imbalanced data. Hence, geneticalgorithms (GA) are recently being combined with traditional classifiers to find useful knowledge for making decision. Although, the main concerns of such GA-based system are the coverage of less search space and increase of computational cost with the growth of population. In this paper, a rule-based knowledge discovery model, combining C4.5 (a Decision Tree based rule inductive algorithm) and a new parallel genetic algorithm based on the idea of massive parallelism, is introduced. The prime goal of the model is to produce a compact set of informative rules from any kind of classification problem. More specifically, the proposed model receives a base method C4.5 to generate rules which are then refined by our proposed parallel GA. The strength of the developed system has been compared with pure C4.5 as well as the hybrid system (C4.5 + sequential geneticalgorithm) on six real world benchmark data sets collected from UCI (University of California at Irvine) machine learning repository. Experiments on data sets validate the effectiveness of the new model. The presented results especially indicate that the model is powerful for volumetric data set. (C) 2011 Elsevier Inc. All rights reserved.
Cloud computing as a novel and entirely internet-based computing platform is emerging and its tenacious challenges become more vivid. A parallel genetic algorithm based method for scheduling tasks with priorities is p...
详细信息
ISBN:
(纸本)9781538675038
Cloud computing as a novel and entirely internet-based computing platform is emerging and its tenacious challenges become more vivid. A parallel genetic algorithm based method for scheduling tasks with priorities is provided in this paper. The goal is to efficiently utilize resources and reduce resource wastage in cloud environments. This is achieved by improving the load balancing rate while better resources are selected to fulfill arrival tasks in a shorter time with lower task failure rate. To evaluate the proposed method, it is simulated using Matlab and compared with two existing methods, a hybrid Ant colony-honey method and a Round Robin (RR) based load balancing method. The results show that the proposed method has 9% - 31% lower energy usage, 14% - 37% lower migration rate and 13%- 17% better Service Level Agreement (SLA) in comparison with the Hybrid and RR method.
暂无评论