Papers by Keyword: Simulated Annealing (SA)

Abstract: In order to improve the classification accuracy of SVM, combination optimization of parameters and character choice for SVM was proposed. Improved QPSO algorithm was researched on in this paper. At the same time, simulated annealing and improved QPSO algorithm was adopted to train SVM in this paper in order to improve its training speed and diagnosis precision. At last the method mentioned above was applied to train and validate SVM using UCI data, and the result showed that this method was very good.

Abstract: Airport gate assignment is to appoint a gate for the arrival or leave flight and to ensure that the flight is on schedule. Assigning the airport gate with high efficiency is a key task among the airport ground busywork. As the core of airport operation, aircraft gate assignment is known as a kind of complicated combinatorial optimization problem. In this paper, we consider the over-constrained Airport Gate Assignment Problem where the number of flights exceeds the number of gates available, and where the objective is to minimize the overall variance of slack time (OVST). According to the intrinsic characteristics of the objective function itself, we design a meta-heuristic method and simulated annealing to solve the problem. Finally, the illustrative examples show the validity of the proposed approach.

Abstract: This paper presents a structural non-probabilistic reliability analysis approach based on a hybrid algorithm of the simulated annealing-particle swarm optimization algorithm and the differential evolution (SAPSO-DE) algorithm. In the structural non-probabilistic reliability analysis, the problem with uncertain parameters can be formulated as an optimization problem using convex model. However, the limit state function is usually implicit for the uncertain parameters. By employing the SAPSO-DE hybrid algorithm based on the evolution of the cognitive and social experiences, the problem of the structural non-probabilistic reliability analysis is solved. A numerical example is given to illustrate the high precision and good feasibility of the present method. The results shows that this proposed approach is effective, and has the predominant capability of global optimization and convergence precision.

Abstract: The existence of specular highlights is a great obstacle of shape-from-Shading. For a single gray-scale image with only intensity information, the existed highlights detection methods based on chroma or polarization analysis cannot directly be applied on it. So, a method using surface shape is provided, it makes full use of the imaging process. Through the surface normal estimation, compute the maximum a posteriori probability of each reflection composition under simulated annealing and detect the highlights areas. Finally, remove the highlights based on the assumption of curvature continuity. Experiments reveal that this method is effective on synthetic and real-world images, improves the accuracy of surface recovery for image combined specular highlights.

Abstract: Algorithms based on Simulated Annealing and Tabu search has been proposed and implemented on scheduling a problem of parallel machines. The identical parallel machine scheduling problem has been considered to minimize the total flow-time subject to optimal makespan. The proposed algorithms have two phases. In the first phase, an initial solution has been obtained using Longest Processing Time (LPT) dispatching rule and in the second phase, simulated annealing and tabu search have been applied to reach a near optimal solution. The performance of the both proposed algorithms have been evaluated by comparing their results for different number of jobs and processing times. The computational results indicate that the proposed Tabu Search algorithm is capable of obtaining better solutions for the given scheduling problem as compared to the Simulated Annealing algorithm. Although both of these algorithms provide the best solutions as compared to the other heuristic algorithms but in comparison of these two; Tabu Search provides the better solutions for the given problem.

Abstract: In order to solve and optimize the task and virtual machine allocation strategy in cloud computing environment, firstly allocation strategy mathematical model, the target of which is the total running time, is established, then a simulated annealing and genetic hybrid algorithm is proposed to solve the mathematical model. The integer coding, a crossover operator, two kinds of mutation operators and the selection mechanism based on simulated annealing strategy are applied in the hybrid algorithm. In the experiments, three sets of data are used to verify the performance of the hybrid algorithm in the Cloudsim software. And the experimental results show that the series of cloud tasks can effectively be assigned to the virtual machine by the hybrid algorithm and the total running time is also minimized by the algorithm.

Abstract: In order to increase calculation accuracy of CNC system reliability, this paper proposed a maximum likelihood parameter estimation method based on improved genetic algorithm. In the parameter estimation process for CNC system reliability distribution model, the maximum likelihood function value was gained by improving genetic algorithm through simulated annealing algorithm. Parameter estimation was carried out by setting Weibull distribution as an example. The result shows that the improved genetic algorithm can increase solution efficiency and convergence rate. Besides, it can effectively estimate parameters of reliability distribution model.

Abstract: The optimization of condenser vacuum is significant to improve efficiency and save energy in the power plant. Taking a 600MW unit as the research object, the condenser vacuum optimization model was established synthetically based on neural network, simulated annealing and biogeography optimization hybrid algorithm (SA-BBO). Circulating pumps power, slight increase of turbine power as well as the market value difference between coal and electric were included in the model. The objective function of the model is to maximize the profit of the power plant. The most effective combinations of the condenser vacuum and the circulating water pump were calculated eventually in different operating conditions by using characteristic analysis of variable condenser conditions. In a certain condition, running three circulating pumps for two steam turbines instead of two pumps can make the condenser vacuum reduce 0.49kPa, and increase revenue 110.2 yuan/h.

Abstract: Job shop scheduling problems are immensely complicated problems in machine scheduling area, and they are classified as NP-hard problems. Finding optimal solutions for job shop scheduling problems with exact methods incur high cost, therefore, looking for approximate solutions with meta-heuristics are favored instead. In this paper, a hybrid framework which is based on a combination of genetic algorithm and simulated annealing is proposed in order to minimize maximum completion time i.e. makespan. In the proposed algorithm, precedence preserving order-based crossover is applied which is able to generate feasible offspring. Two types of mutation operators namely swapping and insertion mutation are used in order to maintain diversity of population and to perform intensive search. Furthermore, a new approach is applied for arranging operations on machines, which improved solution quality and decreased computational time. The proposed hybrid genetic algorithm is tested with a set of benchmarking problems, and simulation results revealed efficiency of the proposed hybrid genetic algorithm compared to conventional genetic based algorithm.

Abstract: This study attempted to develop a control strategy in order to minimize the traffic delay caused by the traffic incident. The proposed strategy controls traffic in terms of providing a combination of different types of incident information. We used the cell transmission model as the underlying traffic flow model to take into accounts the traffic dynamic and use the simulated annealing algorithm to seek the optimal combination of the incident information. The numerical examples confirmed that providing incident information through the proposed control strategy can significantly reduce the traffic delay.